Indication method and apparatus for ai model transmission, and communication device and storage medium

Abstract

The present application belongs to the technical field of wireless communications. Disclosed are an indication method and apparatus for AI model transmission, and a communication device and a storage medium. The indication method comprises: a first communication device sending first information, which indicates whether it is necessary to receive first model information of a target AI model, or which instructs a second communication device to determine whether it is necessary to send the first model information of the target AI model, wherein the first information comprises at least one of the following: identification information of the target AI model; identification information of the first model information; identification information of second model information of the target AI model; timestamp information of the first model information; receiving state information of the first model information; first indication information, which is used for explicitly indicating whether it is necessary to receive the first model information of the target AI model, or explicitly instructing the second communication device to determine whether it is necessary to send the first model information of the target AI model; and second indication information, which is used for indicating whether reception of the first model information is supported.

Description

Indication method, apparatus, and communication device for AI model transmission, and storage medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese Patent Application No. 202411086906.X, filed on August 8, 2024, the entire contents of which are incorporated herein by reference. TECHNICAL FIELD

[0003] The present application belongs to the technical field of wireless communication, and specifically relates to an indication method, apparatus, communication device and storage medium for AI model transmission. BACKGROUND

[0004] Artificial intelligence (AI) is currently widely used in various fields. Integrating artificial intelligence into wireless communication networks can significantly improve technical indicators such as throughput, latency, and user capacity, and is an important task for future wireless communication networks.

[0005] AI technology can be applied to network optimization and other aspects, for example, by analyzing network data through an AI model, predicting and solving potential network problems, thereby improving the stability and performance of the network. When applying an AI model, in some cases, AI model transmission needs to be performed between a terminal and a network side device, or between network side devices. Currently, in AI model transmission, the entire model information (such as model structure and model parameters) of the AI model is generally always transmitted by default, but in fact, in some cases, the receiver of the AI model has already received the model structure and / or model parameters of the current AI model and no longer needs the repeated transmission of the model structure and / or model parameters. Therefore, always transmitting the entire model information of the AI model can cause waste of network resources. SUMMARY

[0006] Embodiments of the present application provide an indication method, apparatus, communication device and storage medium for AI model transmission, which can solve the problem of waste of network resources caused by always transmitting the entire model information of the AI model when transmitting the AI model.

[0007] In a first aspect, an indication method for AI model transmission is provided, comprising:

[0008] A first communication device transmits first information, the first information indicating whether first model information of a target AI model needs to be received, or indicating a second communication device to determine whether the first model information of the target AI model needs to be transmitted;

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

[0010] identification information of the target AI model;

[0011] identification information of the first model information;

[0012] identification information of the second model information of the target AI model;

[0013] timestamp information of the first model information;

[0014] reception state information of the first model information;

[0015] first indication information, used for explicitly indicating whether the first model information of the target AI model needs to be received, or explicitly indicating whether the second communication device needs to send the first model information of the target AI model;

[0016] second indication information, used for indicating whether the first model information needs to be received.

[0017] In a second aspect, an indication method of AI model transmission is provided, including:

[0018] The second communication device receives first information, the first information indicating whether the first communication device needs to receive the first model information of the target AI model, or indicating whether the second communication device needs to send the first model information of the target AI model;

[0019] The first information includes at least one of the following:

[0020] identification information of the target AI model;

[0021] identification information of the first model information;

[0022] identification information of the second model information of the target AI model;

[0023] timestamp information of the first model information;

[0024] reception state information of the first model information;

[0025] first indication information, used for explicitly indicating whether the first model information of the target AI model needs to be received, or explicitly indicating whether the second communication device needs to send the first model information of the target AI model;

[0026] second indication information, used for indicating whether the first model information needs to be received.

[0027] In a third aspect, an indication device of AI model transmission is provided, including:

[0028] The sending module is configured to send first information, the first information indicating whether first model information of a target AI model needs to be received or indicating whether the second communication device judges whether the first model information of the target AI model needs to be sent.

[0029] The first information includes at least one of the following:

[0030] identifier information of the target AI model;

[0031] identifier information of the first model information;

[0032] identifier information of second model information of the target AI model;

[0033] timestamp information of the first model information;

[0034] reception state information of the first model information;

[0035] first indication information, used for explicitly indicating whether the first model information of the target AI model needs to be received or explicitly indicating whether the second communication device judges whether the first model information of the target AI model needs to be sent;

[0036] second indication information, used for indicating whether the first model information is supported to be received.

[0037] In a fourth aspect, an indication device for AI model transmission is provided, including:

[0038] The receiving module is configured to receive first information, the first information indicating whether first model information of a target AI model needs to be received by a first communication device or indicating whether a second communication device judges whether the first model information of the target AI model needs to be sent.

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

[0040] identifier information of the target AI model;

[0041] identifier information of the first model information;

[0042] identifier information of second model information of the target AI model;

[0043] timestamp information of the first model information;

[0044] reception state information of the first model information;

[0045] first indication information, used for explicitly indicating whether the first model information of the target AI model needs to be received or explicitly indicating whether the second communication device judges whether the first model information of the target AI model needs to be sent;

[0046] second indication information, used for indicating whether receiving the first model information is supported.

[0047] In a fifth aspect, an indication apparatus for AI model transmission is provided. The apparatus is configured to perform the steps of the method according to the first aspect, or implement the steps of the method according to the second aspect.

[0048] In a sixth aspect, a communication device is provided. The terminal includes a processor and a memory. The memory stores programs or instructions executable on the processor. When the programs or instructions are executed by the processor, the steps of the method according to the first aspect are implemented.

[0049] In a seventh aspect, a communication device is provided. The communication device includes a processor and a communication interface. The communication interface is configured to send first information. The first information indicates whether first model information of a target AI model needs to be received, or indicates whether a second communication device needs to send the first model information of the target AI model.

[0050] The first information includes at least one of the following:

[0051] identification information of the target AI model;

[0052] identification information of the first model information;

[0053] identification information of second model information of the target AI model;

[0054] timestamp information of the first model information;

[0055] reception status information of the first model information;

[0056] first indication information, used for explicitly indicating whether the first model information of the target AI model needs to be received, or explicitly indicating whether the second communication device needs to send the first model information of the target AI model;

[0057] second indication information, used for indicating whether receiving the first model information is supported.

[0058] In an eighth aspect, a communication device is provided. The communication device includes a processor and a memory. The memory stores programs or instructions executable on the processor. When the programs or instructions are executed by the processor, the steps of the method according to the second aspect are implemented.

[0059] In a ninth aspect, a communication device is provided, including a processor and a communication interface, wherein the communication interface is configured to receive first information, the first information indicating whether a first communication device needs to receive first model information of a target AI model, or indicating whether the second communication device needs to send the first model information of the target AI model;

[0060] The first information includes at least one of the following:

[0061] The identification information of the target AI model;

[0062] The identification information of the first model information;

[0063] The identification information of the second model information of the target AI model;

[0064] The timestamp information of the first model information;

[0065] The receiving state information of the first model information;

[0066] The first indication information explicitly indicates whether the first model information of the target AI model needs to be received, or explicitly indicates whether the second communication device needs to send the first model information of the target AI model;

[0067] The second indication information indicates whether the first model information is supported to be received.

[0068] In a tenth aspect, a readable storage medium is provided, the readable storage medium stores a program or instructions, the program or instructions are executed by a processor to implement the steps of the method according to the first aspect, or implement the steps of the method according to the second aspect.

[0069] In an eleventh aspect, a wireless communication system is provided, including a first communication device and a second communication device, the first communication device is configured to implement the steps of the method according to the first aspect, and the second communication device is configured to implement the steps of the method according to the second aspect.

[0070] In a twelfth aspect, a chip is provided, the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to run a program or instructions to implement the method according to the first aspect, or implement the method according to the second aspect.

[0071] In a thirteenth aspect, a computer program / program product is provided, the computer program / program product is stored in a storage medium, and the computer program / program product is executed by at least one processor to implement the steps of the method according to the first aspect or the second aspect.

[0072] In the embodiments of the present application, the first communication device sends first information to the second communication device, the first information indicates whether the first model information of the target AI model needs to be received, or indicates the second communication device to determine whether the first model information of the target AI model needs to be sent, so that the second communication device can determine whether to send the first model information of the target AI model to the first communication device according to the first information, that is, the first communication device can determine whether to send the first model information of the target AI model to the second communication device according to the actual situation of the first communication device, so as to avoid repeated transmission of the model information that has been transmitted, and reduce the signaling overhead in the network. BRIEF DESCRIPTION OF DRAWINGS

[0073] FIG. 1 is a block diagram of a wireless communication system to which embodiments of the present application can be applied;

[0074] FIG. 2 is a schematic diagram of a neural network;

[0075] FIG. 3 is a schematic diagram of a neuron;

[0076] FIG. 4 is a flowchart of an indication method of AI model transmission according to an embodiment of the present application;

[0077] FIG. 5 is a flowchart of an indication method of AI model transmission according to another embodiment of the present application;

[0078] FIG. 6 is a schematic diagram of an indication device of AI model transmission according to an embodiment of the present application;

[0079] FIG. 7 is a schematic diagram of an indication device of AI model transmission according to another embodiment of the present application;

[0080] FIG. 8 is a schematic diagram of a communication device according to an embodiment of the present application;

[0081] FIG. 9 is a schematic diagram of a hardware structure of a terminal according to an embodiment of the present application;

[0082] FIG. 10 is a schematic diagram of a hardware structure of a network-side device according to an embodiment of the present application;

[0083] FIG. 11 is a schematic diagram of a hardware structure of a network-side device according to another embodiment of the present application. DETAILED DESCRIPTION

[0084] The technical solutions in the embodiments of the present application will be described clearly below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art belong to the scope of protection of the present application.

[0085] The terms "first," "second," etc., used in this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same class, not limited in number; for example, the first object can be one or more. Furthermore, "or" in this application indicates at least one of the connected objects. For example, the scope of protection for "A or B" covers at least three scenarios: Scenario 1: including A but not B; Scenario 2: including B but not A; Scenario 3: including both A and B. In addition, the terms "A and / or B," "at least one of A and B," and "at least one of A or B" also cover at least the above three scenarios. The character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0086] The term "instruction" in this application can be either a direct instruction (or explicit instruction) or an indirect instruction (or implicit instruction). A direct instruction can be understood as one in which the sender explicitly informs the receiver of specific information, the operation to be performed, or the requested result, etc., in the instruction sent. An indirect instruction can be understood as one in which the receiver determines the corresponding information based on the instruction sent by the sender, or makes a judgment and determines the operation to be performed or the requested result, etc., based on the judgment result.

[0087] 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

[0088] ​FIG. 1 shows a block diagram of a wireless communication system to which embodiments of the present application can be applied. The wireless communication system includes a terminal 11 and a network-side device 12. 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 palmtop 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 (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 kiosk, 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 clothes, etc. 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, etc. It should be noted that the specific type of the terminal 11 is not limited in the embodiments of the present application. The network-side device 12 can include an access network device or a core network device. 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.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 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 terminology in the art, and is not limited to a particular technical terminology, provided that the same technical effect is achieved. 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.

[0089] 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.

[0090] 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).

[0091] First, the technical terms involved in the present application will be described.

[0092] I. Artificial Intelligence (AI)

[0093] Artificial intelligence has been widely applied in various fields. Integrating artificial intelligence into wireless communication networks can significantly improve technical indicators such as throughput, latency, and user capacity, and is an important task for future wireless communication networks.

[0094] The algorithms used by the AI module have various types, such as neural networks, decision trees, support vector machines, and Bayesian classifiers. The present application takes the neural network as an example to illustrate the algorithm used by the AI module, but does not limit the specific type of algorithm used by the AI module.

[0095] A schematic diagram of a neural network is shown in FIG. 2. The neural network is composed of neurons, and a schematic diagram of a neuron is shown in FIG. 3. α1, α2…α K are inputs, w1, w2…w K are weights (multiplicative coefficients), b is a bias (additive coefficient), and σ(.) is an activation function. Common activation functions include Sigmoid, tanh, ReLU, etc.

[0096] The parameters of the neural network are optimized by a gradient optimization algorithm. Gradient optimization algorithms are a class of algorithms that minimize or maximize an objective function (sometimes also called a 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, a neural network model f(.) is constructed. With the model, the predicted output f(X) can be obtained according to the input X, and the difference between the predicted value and the true value (f(X)-Y) can be calculated, which is the loss function. Our goal is to find appropriate W, b, so that the value of the above loss function reaches the minimum, and the smaller the loss value, the closer the model is to the true situation.

[0097] The common optimization algorithm at present is basically based on error back propagation (BP) algorithm. The basic idea of BP algorithm is that the learning process consists of two processes of forward propagation of signals and backward propagation of errors. When forward propagating, 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 entered. The error back propagation is to transmit the output error to the input layer through the hidden layer in a certain form, and allocate the error to all units of each layer to obtain the error signal of each unit, which is used as the basis for correcting the weights of each unit. The weight adjustment process of each layer is repeated. The process of continuously adjusting the weights is the learning and training process of the network. This process continues until the output error of the network is reduced to an acceptable level or the preset learning times are reached.

[0098] The common optimization algorithm includes gradient descent, stochastic gradient descent (SGD), mini-batch gradient descent, momentum method, Nesterov (the name of the inventor, specifically stochastic gradient descent with momentum), adaptive gradient descent (Adagrad), Adadelta, root mean square prop (RMSprop), adaptive moment estimation (Adam), etc.

[0099] When the error back propagation is performed, the error / loss obtained from the loss function is used to derive the current neuron, and the gradient is obtained by adding the learning rate, the previous gradient / derivative / partial derivative, etc. The gradient is transmitted to the previous layer.

[0100] II. AI unit / AI model

[0101] The AI unit / AI model described in the present application can also be referred to as an AI unit, an AI model, a machine learning (ML) model, an ML unit, an AI structure, an AI function, an AI feature, a machine learning model, a neural network, a neural network function, a neural network function, etc., or the AI unit / AI model can also refer to a processing unit capable of implementing specific algorithms, formulas, features, processing flows, capabilities, etc. related to AI, or the AI unit / AI model can be a processing method, algorithm, function, feature, module or unit for a specific data set, or the AI unit / AI model can be a processing method, algorithm, function, feature, module or unit running on AI / ML related hardware such as a Graphics Processing Unit (GPU), a Neural Processing Unit (NPU), a Tensor Processing Unit (TPU), or an Application-Specific Integrated Circuit (ASIC), etc. The present application does not make specific limitations. Optionally, the specific data set includes the input and / or output of the AI unit / AI model.

[0102] Optionally, the identifier of the AI unit / AI model can be an AI model identifier, an AI parameter identifier, an AI structure identifier, an AI algorithm identifier, or an identifier of a specific data set associated with the AI unit / AI model, or an identifier of a specific scene, environment, area, cell, channel feature, device related to AI / ML, or an identifier of a function, feature, capability or module related to AI / ML. The present application does not make specific limitations.

[0103] The indication method, device, communication device and storage medium for AI model transmission provided by the embodiments of the present application will be described in detail below in combination with the drawings and some embodiments and their application scenarios.

[0104] Please refer to FIG. 4, the present application embodiment provides an indication method for AI model transmission, comprising:

[0105] Step 41: The first communication device sends first information, the first information indicates whether the first model information of the target AI model needs to be received, or indicates the second communication device to judge whether the first model information of the target AI model needs to be sent;

[0106] The first information includes at least one of the following:

[0107] The identifier information of the target AI model;

[0108] identification information of the first model information of the target AI model;

[0109] identification information of the second model information of the target AI model;

[0110] timestamp information of the first model information;

[0111] receiving state information of the first model information;

[0112] first indication information, used for explicitly indicating whether the first model information of the target AI model needs to be received, or explicitly indicating whether the second communication device judges whether the first model information of the target AI model needs to be sent;

[0113] second indication information, used for indicating whether the first model information needs to be received. Wherein, supporting receiving the first model information can also be called supporting model transfer, or supporting model update, or supporting first model information transfer, or supporting first model information update, etc.

[0114] Optionally, the first communication device can be a terminal or a network side device, and the network side device can be an access network device or a core network device.

[0115] Optionally, the second communication device can be a network side device or a terminal, and the network side device can be an access network device or a core network device.

[0116] For example, in some embodiments, optionally, the first communication device is a terminal, and the second communication device is an access network device.

[0117] In some embodiments, optionally, the first communication device is a terminal, and the second communication device is a core network device.

[0118] In some embodiments, optionally, the first communication device is an access network device, and the second communication device is a core network device.

[0119] In the embodiments of the present application, the first communication device sends first information to the second communication device, the first information indicates whether the first model information of the target AI model needs to be received, or indicates the second communication device to judge whether the first model information of the target AI model needs to be sent, so that the second communication device can determine whether to send the first model information of the target AI model to the first communication device according to the first information, that is, the first communication device can avoid repeated transmission of the model information which has been transmitted and reduce the signaling overhead in the network according to whether the second communication device needs to send the first model information of the target AI model.

[0120] The "identification information" in the embodiments of the present application can be identifier (ID) or name information, etc. For example, the identification information of the target AI model can be the ID of the target AI model, or the name of the target AI model, etc.

[0121] In the embodiments of the present application, the identification information of the target AI model, the identification information of the first model information, and / or the identification information of the second model information of the target AI model can explicitly indicate the model information that needs to be transmitted.

[0122] In some embodiments, optionally, the first model information includes at least one of: at least part of the model structure and at least part of the model parameter.

[0123] In some embodiments, optionally, the second model information includes at least one of: at least part of the model structure and at least part of the model parameter; and the first model information and the second model information are different.

[0124] For example, the first model information is at least part of the model parameter, and the second model information is at least part of the model structure.

[0125] The first model information is at least part of the model structure, and the second model information is at least part of the model parameter.

[0126] The first model information is a part of the model parameter, the second model information is at least part of the model structure and another part of the model parameter.

[0127] The first model information is a part of the model structure, the second model information is another part of the model structure and at least part of the model parameter.

[0128] The first model information is a part of the model parameter and a part of the model structure, and the second model information is another part of the model structure and another part of the model parameter.

[0129] Some examples of the model parameter can include: weights in a neural network, support vectors in a support vector machine, coefficients in linear regression or logistic regression, etc. Taking the above neural network as an example, the model parameter may, for example, include the weights w and the bias b of the neurons of the neural network.

[0130] The model structure refers to the specific framework or architecture of the model, for example, including various layers, nodes, weights, connections, etc. elements of the model, and their layout and organization.

[0131] In the embodiments of the present application, the first communication device can request the second communication device to send at least part of the model parameter and / or at least part of the model structure according to its own needs, so as to avoid the repeated transmission of the model parameter without transmitting the entire AI model each time.

[0132] In some embodiments, optionally, the timestamp information comprises at least one of:

[0133] an update time;

[0134] a sending time;

[0135] a receiving time;

[0136] a valid time;

[0137] a training time;

[0138] a marking time;

[0139] a publishing time.

[0140] In some embodiments, the update time, the sending time and / or the receiving time is determined by the first communication device. In some embodiments, the valid time, the training time, the marking time and / or the publishing time is indicated by the second communication device.

[0141] In some embodiments, the valid time can be a valid time period, a valid deadline, or the like.

[0142] In some embodiments, the training time can be a training start time, a training completion time, or the like.

[0143] In some embodiments, the marking time can be a time marked by the second communication device. For example, the marking time can implicitly indicate the valid time, the training time, the publishing time, or the like, which is not limited herein.

[0144] In some embodiments, the timestamp information of the first model information can enable the second communication device to determine whether the first model information of the first communication device is the latest first model information, so as to determine whether the first model information needs to be transmitted.

[0145] In some embodiments, the first indication information can explicitly indicate whether the first model information of the target AI model needs to be received, or explicitly indicate whether the second communication device needs to send the first model information of the target AI model, so that the second communication device does not need to perform additional determination, but only needs to determine whether to transmit the first model information according to the indication in the first information.

[0146] In some embodiments, the second indication information can indicate whether the first model information needs to be received. If the second indication information indicates that the first model information does not need to be received, the second communication device can determine that the first model information does not need to be transmitted according to the second indication information.

[0147] In some embodiments, optionally, the receiving status information comprises at least one of:

[0148] 1) a first state, indicating that the target AI model can be used directly, or, indicating that the target AI model can be run, or, indicating that the first model information has been received, or, indicating that the first model information does not need to be received, or, indicating that the second communication device does not need to send the first model information;

[0149] wherein, indicating that the target AI model can be used directly, can implicitly indicate that the first model information does not need to be received, or, the second communication device does not need to send the first model information.

[0150] wherein, indicating that the target AI model can be run, can implicitly indicate that the first model information does not need to be received, or, the second communication device does not need to send the first model information.

[0151] wherein, indicating that the first model information has been received, can implicitly indicate that the first model information does not need to be received, or, the second communication device does not need to send the first model information.

[0152] wherein, the above "the first model information does not need to be received" can include that new (such as newly trained, newly distributed, latest version, etc.) first model information does not need to be received.

[0153] wherein, the above "the second communication device does not need to send the first model information" can include that the second communication device does not need to send new (such as newly trained, newly distributed, latest version, etc.) first model information.

[0154] 2) a second state, indicating that the first model information has not been received, or, indicating that the second communication device needs to send the first model information;

[0155] wherein, indicating that the first model information has not been received, can implicitly indicate that the second communication device needs to send the first model information.

[0156] 3) a third state, indicating that the first model information has been received, but the second communication device needs to send the first model information;

[0157] wherein, the above "the second communication device needs to send the first model information" can include that the second communication device needs to send new (such as newly trained, newly distributed, latest version, etc.) first model information.

[0158] 4) a fourth state, indicating that the first model information has been received, but the second communication device needs to determine whether the first model information needs to be sent.

[0159] The "need for the second communication device to determine whether to send the first model information" can include a need for the second communication device to determine whether to send new (e.g., newly trained, newly released, or newly versioned) first model information.

[0160] In some embodiments, at least one of the first state, the second state, the third state, and the fourth state further indicates that the target AI model, the second model information of the target AI model, or the first model information of the target AI model supports model transfer or model parameter updating.

[0161] In some embodiments, the first information includes at least one of identification information of the target AI model and identification information of the second model information, and reception state information of the first model information, the reception state information including one of the first state, the second state, the third state, and the fourth state.

[0162] For example, the first information includes identification information (e.g., ID5) of the target AI model and the first state of the first model information. This indicates that the target AI model in the first communication device can be used directly, or the first communication device can run the target AI model, or the first communication device has received the first model information, or the first communication device does not need to receive the first model information, or the first communication device does not need the second communication device to send the first model information.

[0163] In some embodiments, the first information includes at least one of identification information of the target AI model and identification information of the second model structure, identification information of the first model information, and reception state information of the first model information, the reception state information including one of the first state, the third state, and the fourth state.

[0164] For example, the first information includes identification information (e.g., ID5) of the target AI model, identification information (e.g., model parameter 6) of the first model information, and the third state of the first model information. This indicates that the first communication device has received the first model information, but needs the second communication device to send the first model information.

[0165] In some embodiments, optionally, the first information comprises at least one of the following: identification information of the target AI model, identification information of the second model structure, identification information of the first model information, and timestamp information of the first model information, and the first information is used to indicate that the receiving state information of the first model information is the fourth state.

[0166] For example, the first information comprises the following: identification information of the target AI model (such as ID 5), identification information of the first model information (such as model parameter 6), and timestamp information of the first model information. In this case, it is indicated that the receiving state of the first model information of the first communication device is the fourth state, i.e., the first model information has been received, but the second communication device needs to determine whether to send the first model information according to the timestamp information of the first model information.

[0167] In the above embodiments, the receiving state information of the first model information can be directly indicated in the first information or indicated by the timestamp, so that the second communication device can perform different operations according to different receiving state information.

[0168] In some embodiments, optionally, the first information indicates that the receiving state information of the first model information is the first state by at least one of the following:

[0169] identification information of the target AI model;

[0170] identification information of the first model information;

[0171] identification information of the second model information.

[0172] That is, the first communication device implicitly indicates that the receiving state of the first model information is the first state by at least one of the above information, so that the second communication device does not send the first model information of the target AI model to the first communication device according to the first state of the first model information.

[0173] In some embodiments, optionally, the first information indicates that the receiving state information of the first model information is the second state by at least one of the following:

[0174] identification information of the target AI model;

[0175] identification information of the second model information.

[0176] That is, the first communication device implicitly indicates that the receiving state of the first model information is the second state by at least one of the above information, so that the second communication device sends the first model information of the target AI model to the first communication device according to the second state of the first model information.

[0177] In some embodiments, optionally, the first information indicates that the receiving state information of the first model information is in the third state through at least one of the following:

[0178] identification information of the target AI model;

[0179] identification information of the first model information;

[0180] identification information of the second model information.

[0181] That is, the first communication device implicitly indicates that the receiving state of the first model information is in the third state through at least one of the above information, so that the second communication device sends the first model information of the target AI model to the first communication device according to the third state of the first model information.

[0182] In some embodiments, optionally, the first information indicates that the receiving state information of the first model information is in the fourth state through at least one of the following:

[0183] identification information of the target AI model;

[0184] identification information of the first model information;

[0185] identification information of the second model information;

[0186] timestamp information of the first model information.

[0187] That is, the first communication device implicitly indicates that the receiving state of the first model information is in the fourth state through at least one of the above information, so that the second communication device determines whether to send the first model information of the target AI model to the first communication device according to the fourth state of the first model information.

[0188] In some embodiments, optionally, the indication method of the AI model transmission further includes: after the first communication device receives new first model information, determining whether the previously received first model information is still available or unavailable. Thus, the previously received first model information can be used or not used as needed subsequently. The "previously received" refers to the one received before the new first model information.

[0189] In some embodiments, optionally, after the first communication device receives new first model information, it determines whether the previously received first model information is still available or unavailable, including:

[0190] The first communication device receives third indication information, and the third indication information is used to indicate whether the previously received first model information is available after receiving the new first model information;

[0191] The first communication device determines whether the previously received first model information is still available or unavailable according to the third indication information after receiving the new first model information.

[0192] That is, the first communication device is indicated by the second communication device whether the previously received first model information is available or unavailable.

[0193] The second communication device can indicate that the previously received first model information is available, or can indicate that the previously received first model information is unavailable.

[0194] In some embodiments, after the first communication device receives the new first model information, the determination of whether the previously received first model information is still available or unavailable includes: the first communication device determines whether the previously received first model information is still available or unavailable according to a protocol agreement after receiving the new first model information.

[0195] Optionally, the protocol agreement indicates that the previously received first model information is still available, or the protocol agreement indicates that the previously received first model information is unavailable. In the case of the protocol agreement, the two are mutually exclusive, either available or unavailable.

[0196] In some embodiments, the indication method of the AI model transmission further includes: after the first communication device receives the new first model information, the fourth indication information is sent, and the fourth indication information is used to indicate whether the previously received first model information of the first communication device is available. That is, the first communication device itself determines whether the previously received first model information is available, and indicates the second communication device.

[0197] The first communication device can indicate that the previously received first model information is available, or can indicate that the previously received first model information is unavailable.

[0198] In some embodiments, at least one of the content, format and rule of the first information is agreed by a protocol, offline or air interface interaction. Optionally, the air interface interaction can be the first communication device reporting to the second communication device, or the second communication device indicating to the first communication device.

[0199] The content of the first information refers to what content the first information includes. For example, whether to include the identification information of the first model parameter, etc.

[0200] The format of the first information refers to the name, length and data type of each field in the first information.

[0201] In some embodiments, optionally, the target AI model comprises at least one of:

[0202] a first AI model used by the first communication device;

[0203] a reference AI model of the first AI model;

[0204] a second AI model, the second AI model being an AI model used by the first communication device or a test device in testing;

[0205] a reference AI model of the second AI model;

[0206] a third AI model, the third AI model being an AI model used by the first communication device or the test device to match the second AI model;

[0207] a reference AI model of the third AI model.

[0208] The reference AI model can be an initial AI model that has not been trained, or a standard AI model, etc.

[0209] The third AI model is applied to a two-end communication use case (such as a channel state information (CSI) compression and recovery, encoding and decoding, etc. scene, for example, the second AI model used in testing is a CSI encoder, and the third AI model is a CSI decoder.

[0210] In some embodiments, optionally, the target AI model is used for one of:

[0211] 1) reference signal processing;

[0212] The reference signal processing includes at least one of signal detection, filtering, equalization, etc., and 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 (PTRS), etc.

[0213] 2) Channel signal transmission, reception, demodulation, and / or sending;

[0214] The channel includes at least one of 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 physical broadcast channel (PBCH), etc.

[0215] 3) Channel state information acquisition;

[0216] The channel state information acquisition includes at least one of:

[0217] 3a) Channel State Information feedback, including at least one of: channel related information, channel matrix related information, channel eigen-information, channel matrix eigen-information, Precoding Matrix Indicator (PMI), Rank Indication (RI), CSI-RS resource indicator (CRI), Channel Quality Indicator (CQI), Layer Indicator (LI), etc.

[0218] 3b) Frequency Division Duplexing (FDD) uplink-downlink partial reciprocity. For FDD system, according to partial reciprocity, the base station can inform the terminal of the angle information and time delay information through the method of CSI-RS precoding or direct indication, according to which the terminal reports or selects and reports within the indication range of the base station, thereby reducing the calculation amount of the terminal and the overhead of Channel State Information (CSI) reporting.

[0219] 4) Beam management;

[0220] The beam management includes at least one of: beam measurement, beam reporting, beam prediction (spatial domain prediction or frequency domain prediction), beam failure detection, beam failure recovery, new beam indication in beam failure recovery.

[0221] 5) Channel prediction;

[0222] The channel prediction includes at least one of: channel state information prediction, beam prediction.

[0223] 6) Channel and / or source coding;

[0224] The channel and / or source coding includes at least one of: channel coding, channel decoding, source coding, source decoding, joint source-channel coding, joint source-channel decoding.

[0225] 7) Interference suppression;

[0226] The interference suppression includes at least one of: intra-cell interference, inter-cell interference, out-of-band interference, intermodulation interference, etc.

[0227] 8) Positioning;

[0228] The positioning can be a specific position (including horizontal position and / or vertical position) or a future possible trajectory of the terminal estimated by a reference signal (e.g., SRS), or information assisting the position estimation or trajectory estimation, such as Timing of Arrival (TOA), line of sight or non-line of sight, or Reference Signal Time Difference (RSTD).

[0229] 9) Prediction and / or management of higher layer services and / or parameters;

[0230] The parameters may, for example, include at least one of the following: throughput, required data packet size, service demand, moving speed, noise information, etc.

[0231] 10) Encoding and / or parsing of control signaling.

[0232] The control signaling may, for example, include at least one of the following: power control related signaling, beam management related signaling.

[0233] Referring to FIG. 5, the embodiment of the present application further provides an indication method of AI model transmission, comprising:

[0234] Step 51: The second communication device receives first information, the first information indicating whether the first communication device needs to receive first model information of a target AI model, or indicating whether the second communication device needs to send the first model information of the target AI model;

[0235] The first information may, for example, include at least one of the following:

[0236] The identification information of the target AI model;

[0237] The identification information of the first model information;

[0238] The identification information of the second model information of the target AI model;

[0239] The timestamp information of the first model information;

[0240] The reception state information of the first model information;

[0241] The first indication information explicitly indicates whether the first model information of the target AI model needs to be received, or explicitly indicates whether the second communication device needs to send the first model information of the target AI model;

[0242] The second indication information indicates whether the first model information is supported to be received.

[0243] In the embodiments of the present application, the second communication device receives the first information sent by the first communication device, the first information indicating whether the first model information of the target AI model needs to be received, or indicating the second communication device to determine whether the first model information of the target AI model needs to be sent, so that the second communication device can determine whether to send the first model information of the target AI model to the first communication device according to the first information, that is, the first communication device can determine whether the second communication device needs to send the first model information of the target AI model according to the actual situation of the first communication device, so as to avoid repeated transmission of the model information that has been transmitted and reduce the signaling overhead in the network.

[0244] Optionally, the first model information includes at least one of the following: at least part of the model structure and at least part of the model parameters.

[0245] Optionally, the second model information includes at least one of the following: at least part of the model structure and at least part of the model parameters; and the first model information and the second model information are different.

[0246] Optionally, the timestamp information includes at least one of the following:

[0247] update time;

[0248] sending time;

[0249] receiving time;

[0250] valid time;

[0251] training time;

[0252] labeling time;

[0253] publishing time.

[0254] Optionally, the receiving state information includes at least one of the following:

[0255] a first state indicating that the target AI model can be directly used, or indicating that the target AI model can be run, or indicating that the first model information has been received, or indicating that the first model information does not need to be received, or indicating that the second communication device does not need to send the first model information;

[0256] a second state indicating that the first model information has not been received, or indicating that the second communication device needs to send the first model information;

[0257] a third state indicating that the first model information has been received, but the second communication device needs to send the first model information;

[0258] The fourth state indicates that the first model information has been received, but the second communication device needs to determine whether to send the first model information.

[0259] Optionally, the first information includes at least one of identification information of the target AI model and identification information of the second model information, and the receiving state information of the first model information, the receiving state information including one of the first state, the second state, the third state, and the fourth state.

[0260] Alternatively,

[0261] The first information includes at least one of identification information of the target AI model and identification information of the second model structure, and identification information of the first model information, and the receiving state information of the first model information, the receiving state information including one of the first state, the third state, and the fourth state.

[0262] Alternatively,

[0263] The first information includes at least one of identification information of the target AI model and identification information of the second model structure, and identification information of the first model information, and the timestamp information of the first model information, the first information being used to indicate that the receiving state information of the first model information is the fourth state.

[0264] Optionally, the first information indicates that the receiving state information of the first model information is the first state by at least one of the following:

[0265] The identification information of the target AI model;

[0266] The identification information of the first model information;

[0267] The identification information of the second model information;

[0268] Alternatively,

[0269] The first information indicates that the receiving state information of the first model information is the second state by at least one of the following:

[0270] The identification information of the target AI model;

[0271] The identification information of the second model information;

[0272] Alternatively,

[0273] The first information indicates that the receiving state information of the first model information is the third state by at least one of the following:

[0274] The identification information of the target AI model;

[0275] The identification information of the first model information;

[0276] The identification information of the second model information;

[0277] Or,

[0278] The first information indicates that the receiving state information of the first model information is the fourth state through at least one of the following:

[0279] The identification information of the target AI model;

[0280] The identification information of the first model information;

[0281] The identification information of the second model information;

[0282] The timestamp information of the first model information.

[0283] Optionally, the indication method of the AI model transmission further includes that the second communication device determines whether to send the first model information of the AI model according to the first information.

[0284] Optionally, the indication method of the AI model transmission further includes that the second communication device sends third indication information, and the third indication information is used to indicate whether the first model information received before the first communication device receives new first model information is available.

[0285] Optionally, the indication method of the AI model transmission further includes that the second communication device receives fourth indication information, and the fourth indication information is used to indicate whether the first model information received before the first communication device receives new first model is available.

[0286] Optionally, the indication method of the AI model transmission further includes that the second communication device determines whether the first model information received before the first communication device receives new first model information is available according to a protocol agreement.

[0287] Optionally, at least one of the content, format and rule of the first information is determined by a protocol agreement, an offline agreement or air interface interaction.

[0288] Optionally, the target AI model includes at least one of the following:

[0289] The first AI model used by the first communication device;

[0290] The reference AI model of the first AI model;

[0291] a second AI model, the second AI model being an AI model used by the first communication device or test device in testing;

[0292] a reference AI model of the second AI model;

[0293] a third AI model, the third AI model being an AI model used by the first communication device or test device to match the second AI model;

[0294] a reference AI model of the third AI model.

[0295] Optionally, the target AI model is used for one of the following:

[0296] reference signal processing;

[0297] channel signal transmission, reception, demodulation and / or sending;

[0298] channel state information acquisition;

[0299] beam management;

[0300] channel prediction;

[0301] channel and / or source coding;

[0302] interference suppression;

[0303] positioning;

[0304] prediction and / or management of higher layer services and / or parameters;

[0305] encoding and / or parsing of control signaling.

[0306] The AI model transmission indication method provided in the embodiments of the present application can be executed by an AI model transmission indication device. In the embodiments of the present application, the AI model transmission indication method executed by the AI model transmission indication device is taken as an example to illustrate the AI model transmission indication device provided in the embodiments of the present application.

[0307] The AI model transmission indication device provided in the embodiments of the present application can be a communication device or a component in a communication device, for example, a chip. The communication device can be a terminal, a network side device or a server, etc. For example, 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 are not limited specifically.

[0308] The indication device of the AI model transmission 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. For example, the processor can include a general-purpose processor, a special-purpose processor, 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 devices, 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 a transceiver, a pin, a circuit, a bus, a radio frequency unit, etc.

[0309] Specifically, referring to FIG. 6, the embodiment of the present application further provides an indication device 60 of AI model transmission, which includes:

[0310] The sending module 61 sends first information, and the first information indicates whether the first model information of the target AI model needs to be received or indicates the second communication device to determine whether the first model information of the target AI model needs to be sent.

[0311] The first information includes at least one of the following:

[0312] The identification information of the target AI model;

[0313] The identification information of the first model information;

[0314] The identification information of the second model information of the target AI model;

[0315] The timestamp information of the first model information;

[0316] The receiving state information of the first model information;

[0317] The first indication information explicitly indicates whether the first model information of the target AI model needs to be received or explicitly indicates the second communication device to determine whether the first model information of the target AI model needs to be sent.

[0318] The second indication information is used for indicating whether the first model information is supported to be received.

[0319] In the embodiments of the present application, the first information is sent to the second communication device, the first information indicates whether the first model information of the target AI model needs to be received, or indicates the second communication device to determine whether the first model information of the target AI model needs to be sent, so that the second communication device can determine whether to send the first model information of the target AI model to the first communication device according to the first information, that is, the first communication device can determine whether the first model information of the target AI model needs to be sent by the second communication device according to the actual situation of the first communication device, so as to avoid repeated transmission of the model information that has been transmitted, and reduce the signaling overhead in the network.

[0320] Optionally, the first model information includes at least one of the following: at least part of the model structure and at least part of the model parameter.

[0321] The second model information includes at least one of the following: at least part of the model structure and at least part of the model parameter.

[0322] The first model information and the second model information are different.

[0323] Optionally, the timestamp information includes at least one of the following:

[0324] The update time;

[0325] The sending time;

[0326] The receiving time;

[0327] The effective time;

[0328] The training time;

[0329] The marking time;

[0330] The publishing time.

[0331] Optionally, the receiving state information includes at least one of the following:

[0332] The first state indicates that the target AI model can be directly used, or indicates that the target AI model can be run, or indicates that the first model information has been received, or indicates that the first model information does not need to be received, or indicates that the second communication device does not need to send the first model information;

[0333] The second state indicates that the first model information has not been received, or indicates that the second communication device needs to send the first model information;

[0334] a third state indicating that the first model information has been received, but the second communication device needs to send the first model information;

[0335] a fourth state indicating that the first model information has been received, but the second communication device needs to determine whether to send the first model information.

[0336] Optionally, the first information includes at least one of identification information of the target AI model and identification information of the second model information, and the receiving state information of the first model information, the receiving state information including one of the first state, the second state, the third state and the fourth state.

[0337] Alternatively,

[0338] The first information includes at least one of identification information of the target AI model and identification information of the second model structure, and identification information of the first model information, and the receiving state information of the first model information, the receiving state information including one of the first state, the third state and the fourth state.

[0339] Alternatively,

[0340] The first information includes at least one of identification information of the target AI model and identification information of the second model structure, and identification information of the first model information, and the first information indicating that the receiving state information of the first model information is the fourth state.

[0341] Optionally, the first information indicates that the receiving state information of the first model information is the first state by at least one of:

[0342] The identification information of the target AI model;

[0343] The identification information of the first model information;

[0344] The identification information of the second model information;

[0345] Alternatively,

[0346] The first information indicates that the receiving state information of the first model information is the second state by at least one of:

[0347] The identification information of the target AI model;

[0348] The identification information of the second model information;

[0349] Alternatively,

[0350] The first information indicates that the receiving state information of the first model information is the third state through at least one of the following:

[0351] The identification information of the target AI model;

[0352] The identification information of the first model information;

[0353] The identification information of the second model information;

[0354] Or,

[0355] The first information indicates that the receiving state information of the first model information is the fourth state through at least one of the following:

[0356] The identification information of the target AI model;

[0357] The identification information of the first model information;

[0358] The identification information of the second model information;

[0359] The timestamp information of the first model information.

[0360] Optionally, the indication device 60 of the AI model transmission further comprises:

[0361] The processing module is configured to determine whether the previously received first model information is still available or unavailable after receiving the new first model information.

[0362] Optionally, the processing module is configured to receive third indication information, the third indication information being used to indicate whether the previously received first model information is available after receiving the new first model information; and determine whether the previously received first model information is still available or unavailable after receiving the new first model information according to the third indication information.

[0363] Optionally, the processing module is configured to determine whether the previously received first model information is still available or unavailable after receiving the new first model information according to a protocol agreement.

[0364] Optionally, the sending module 61 is further configured to send fourth indication information after receiving the new first model information, the fourth indication information being used to indicate whether the first model information received by the first communication device previously is available.

[0365] Optionally, at least one of the content, format and rule of the first information is determined by a protocol agreement, offline agreement or air interface interaction.

[0366] Optionally, the target AI model comprises at least one of the following:

[0367] a first AI model used by the first communication device;

[0368] a reference AI model of the first AI model;

[0369] a second AI model, the second AI model being an AI model used by the first communication device or a test device in a test;

[0370] a reference AI model of the second AI model;

[0371] a third AI model, the third AI model being an AI model used by the first communication device or a test device for matching the second AI model;

[0372] a reference AI model of the third AI model.

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

[0374] reference signal processing;

[0375] channel signal transmission, reception, demodulation and / or sending;

[0376] channel state information acquisition;

[0377] beam management;

[0378] channel prediction;

[0379] channel and / or source coding;

[0380] interference suppression;

[0381] positioning;

[0382] prediction and / or management of higher layer services and / or parameters;

[0383] encoding and / or parsing of control signaling.

[0384] The indication apparatus 60 for AI model transmission provided by 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 here.

[0385] Specifically, please refer to FIG. 7, the embodiments of the present application further provide an indication apparatus 70 for AI model transmission, comprising:

[0386] a receiving module 71, configured to receive first information, the first information indicating whether the first communication device needs to receive first model information of a target AI model, or indicating whether the second communication device needs to send the first model information of the target AI model;

[0387] The first information includes at least one of the following:

[0388] The identification information of the target AI model;

[0389] The identification information of the first model information;

[0390] The identification information of the second model information of the target AI model;

[0391] The timestamp information of the first model information;

[0392] The receiving state information of the first model information;

[0393] First indication information, used for explicitly indicating whether the first model information of the target AI model needs to be received, or explicitly indicating whether the second communication device needs to send the first model information of the target AI model;

[0394] Second indication information, used for indicating whether the first model information needs to be received.

[0395] In the embodiments of the present application, the first information sent by the first communication device is received, the first information indicates whether the first model information of the target AI model needs to be received, or indicates whether the second communication device needs to send the first model information of the target AI model, so that whether the first model information of the target AI model needs to be sent to the first communication device can be determined according to the first information, that is, the first communication device can determine whether the first model information of the target AI model needs to be sent by the second communication device according to the actual situation of the first communication device, so as to avoid repeated transmission of the model information that has been transmitted, and reduce the signaling overhead in the network.

[0396] Optionally, the first model information includes at least one of the following: at least part of the model structure and at least part of the model parameter;

[0397] The second model information includes at least one of the following: at least part of the model structure and at least part of the model parameter;

[0398] The first model information and the second model information are different.

[0399] Optionally, the timestamp information includes at least one of the following:

[0400] Update time;

[0401] Sending time;

[0402] Receiving time;

[0403] Valid time;

[0404] Training time;

[0405] Tag time;

[0406] Release time.

[0407] Optionally, the receiving state information comprises at least one of:

[0408] a first state, indicating that the target AI model can be directly used, or indicating that the target AI model can be run, or indicating that the first model information has been received, or indicating that the first model information does not need to be received, or indicating that the second communication device does not need to send the first model information;

[0409] a second state, indicating that the first model information has not been received, or indicating that the second communication device needs to send the first model information;

[0410] a third state, indicating that the first model information has been received, but the second communication device needs to send the first model information;

[0411] a fourth state, indicating that the first model information has been received, but the second communication device needs to determine whether the first model information needs to be sent.

[0412] Optionally, the first information comprises at least one of identification information of the target AI model and identification information of the second model information, and the receiving state information of the first model information, the receiving state information comprising one of the first state, the second state, the third state and the fourth state;

[0413] or,

[0414] the first information comprises at least one of identification information of the target AI model and identification information of the second model structure, and identification information of the first model information, and the receiving state information of the first model information, the receiving state information comprising one of the first state, the third state and the fourth state;

[0415] or,

[0416] the first information comprises at least one of identification information of the target AI model and identification information of the second model structure, and identification information of the first model information, and the first information comprises timestamp information of the first model information, the first information being used to indicate that the receiving state information of the first model information is the fourth state.

[0417] Optionally, the first information indicates that the receiving state information of the first model information is the first state by at least one of:

[0418] Identification information of the target AI model;

[0419] Identification information of the first model information;

[0420] Identification information of the second model information;

[0421] Or,

[0422] The first information indicates that the receiving state information of the first model information is the second state through at least one of the following:

[0423] Identification information of the target AI model;

[0424] Identification information of the second model information;

[0425] Or,

[0426] The first information indicates that the receiving state information of the first model information is the third state through at least one of the following:

[0427] Identification information of the target AI model;

[0428] Identification information of the first model information;

[0429] Identification information of the second model information;

[0430] Or,

[0431] The first information indicates that the receiving state information of the first model information is the fourth state through at least one of the following:

[0432] Identification information of the target AI model;

[0433] Identification information of the first model information;

[0434] Identification information of the second model information;

[0435] Timestamp information of the first model information.

[0436] Optionally, the indication device 70 of the AI model transmission further comprises:

[0437] The processing module is configured to determine whether to send the first model information of the target AI model according to the first information.

[0438] Optionally, the indication device 70 of the AI model transmission further comprises:

[0439] The sending module is configured to send third indication information, and the third indication information is used to indicate whether the first model information received before by the first communication device is available after receiving new first model information.

[0440] Optionally, the receiving module 71 is further configured to receive fourth indication information, the fourth indication information being used to indicate whether the first model information received by the first communication device before receiving a new first model is available after receiving the new first model.

[0441] Optionally, at least one of the content, format and rule of the first information is determined by a protocol, offline agreement or air interface interaction.

[0442] Optionally, the target AI model comprises at least one of:

[0443] a first AI model used by the first communication device;

[0444] a reference AI model of the first AI model;

[0445] a second AI model, the second AI model being an AI model used by the first communication device or a test device in a test;

[0446] a reference AI model of the second AI model;

[0447] a third AI model, the third AI model being an AI model used by the first communication device or the test device to match the second AI model;

[0448] a reference AI model of the third AI model.

[0449] Optionally, the target AI model is used for one of:

[0450] reference signal processing;

[0451] channel signal transmission, reception, demodulation and / or sending;

[0452] channel state information acquisition;

[0453] beam management;

[0454] channel prediction;

[0455] channel and / or source coding;

[0456] interference suppression;

[0457] positioning;

[0458] prediction and / or management of higher layer service and / or parameter;

[0459] encoding and / or parsing of control signaling.

[0460] The indication device 70 for AI model transmission provided by the embodiments of the present application can realize each process of the method embodiment of FIG. 5 and achieve the same technical effects. To avoid repetition, details are not described herein.

[0461] As shown in FIG. 8, the embodiments of the present application further provide a communication device 80, which includes a processor 81 and a memory 82, and the memory 82 stores programs or instructions executable on the processor 81. When the programs or instructions are executed by the processor 81, each step of the above-mentioned AI model transmission indication method embodiment is realized, and the same technical effects can be achieved. To avoid repetition, details are not described herein.

[0462] The embodiments of the present application further provide a terminal, which includes a processor and a communication interface, the communication interface and the processor are coupled, and the processor is configured to run programs or instructions to realize the steps in the method embodiments shown in FIG. 4 or FIG. 5. The terminal embodiment corresponds to the above-mentioned first communication device side or second communication device side method embodiment. Each implementation process and implementation manner of the above-mentioned method embodiment can be applied to the terminal embodiment, and the same technical effects can be achieved. The terminal can be the indication device for AI model transmission shown in FIG. 6 or FIG. 7. Specifically, FIG. 9 is a schematic diagram of the hardware structure of a terminal for implementing the embodiments of the present application.

[0463] The terminal 90 includes, but is not limited to, at least part of the components such as a radio frequency unit 91, a network module 92, an audio output unit 93, an input unit 94, a sensor 95, a display unit 96, a user input unit 97, an interface unit 98, a memory 99, and a processor 910.

[0464] Those skilled in the art can understand that the terminal 90 can further include a power supply (such as a battery) for supplying power to each component. The power supply can be logically connected to the processor 910 through a power management system, so as to realize functions such as management of charging, discharging, and power consumption management through the power management system. The terminal structure shown in FIG. 9 does not constitute a limitation on the terminal. The terminal can include more or fewer components than those shown, or combine certain components, or different component arrangements, which are not described herein.

[0465] It should be understood that in the embodiments of the present application, the input unit 94 can include a graphics processor 941 and a microphone 942, and the graphics processor 941 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 96 can include a display panel 961, which can be configured in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit 97 includes at least one of a touch panel 971 and other input devices 972. The touch panel 971 is also called a touch screen. The touch panel 971 can include two parts of a touch detection device and a touch controller. The other input devices 972 can include, 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, and the like, which will not be described here.

[0466] In the embodiments of the present application, after the radio frequency unit 91 receives the downlink data from the network side device, it can be transmitted to the processor 910 for processing. In addition, the radio frequency unit 91 can send uplink data to the network side device. Generally, the radio frequency unit 91 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc.

[0467] The memory 99 can be used to store software programs or instructions and various data. The memory 99 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 99 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 99 in the embodiments of the present application includes but is not limited to these and any other suitable types of memory.

[0468] The processor 910 can include one or more processing units; optionally, the processor 910 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 910.

[0469] The radio frequency unit 91 is configured to send first information, wherein the first information indicates whether first model information of a target AI model needs to be received, or indicates whether the second communication device needs to send the first model information of the target AI model.

[0470] The first information includes at least one of the following:

[0471] The identification information of the target AI model;

[0472] identification information of the first model information of the target AI model;

[0473] identification information of the second model information of the target AI model;

[0474] timestamp information of the first model information;

[0475] reception state information of the first model information;

[0476] first indication information, used for explicitly indicating whether the first model information of the target AI model needs to be received, or explicitly indicating whether the second communication device judges whether the first model information of the target AI model needs to be sent;

[0477] second indication information, used for indicating whether the first model information is supported to be received.

[0478] In the embodiment of the present application, the first information is sent to the second communication device, the first information indicates whether the first model information of the target AI model needs to be received, or indicates the second communication device to judge whether the first model information of the target AI model needs to be sent, so that the second communication device can determine whether to send the first model information of the target AI model to the first communication device according to the first information, that is, the first communication device can avoid repeated transmission of the model information that has been transmitted according to whether the second communication device needs to send the first model information of the target AI model, and reduce the signaling overhead in the network.

[0479] It can be understood that the implementation process of each implementation mode mentioned in the embodiment can refer to the related description of the method embodiment shown in FIG. 4, and achieve the same or corresponding technical effects. To avoid repetition, it will not be repeated here.

[0480] Or, wherein the radio frequency unit 91 is configured to receive first information, the first information indicating whether the first communication device needs to receive the first model information of the target AI model, or indicating the second communication device to judge whether the first model information of the target AI model needs to be sent;

[0481] The first information includes at least one of the following:

[0482] identification information of the target AI model;

[0483] identification information of the first model information of the target AI model;

[0484] identification information of the second model information of the target AI model;

[0485] timestamp information of the first model information;

[0486] reception state information of the first model information;

[0487] The first indication information is used for explicitly indicating whether the first model information of the target AI model needs to be received, or explicitly indicating whether the second communication device judges whether the first model information of the target AI model needs to be sent.

[0488] The second indication information is used for indicating whether the first model information is supported to be received.

[0489] In the embodiment of the present application, the first information sent by the first communication device is received, and the first information indicates whether the first model information of the target AI model needs to be received, or indicates whether the second communication device judges whether the first model information of the target AI model needs to be sent, so that whether the first model information of the target AI model is sent to the first communication device can be determined according to the first information, that is, the first communication device can avoid repeated transmission of the model information that has been transmitted and reduce the signaling overhead in the network according to whether the second communication device needs to send the first model information of the target AI model.

[0490] It can be understood that the implementation processes of each implementation manner mentioned in the embodiment can refer to the related description of the method embodiment shown in FIG. 5, and achieve the same or corresponding technical effects. To avoid repetition, it will not be described here.

[0491] The embodiment of the present application also provides a network side device, which includes a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used for running programs or instructions to realize the steps of the method embodiment shown in FIG. 4 or FIG. 5. The network side device embodiment corresponds to the above-mentioned first communication device or second communication device side method embodiment, and each implementation process and implementation manner of the above-mentioned method embodiment can be applied to the network side device embodiment, and the same technical effects can be achieved.

[0492] Specifically, the embodiment of the present application also provides a network side device, which can be the indication device of AI model transmission shown in FIG. 6 or FIG. 7. As shown in FIG. 10, the network side device 100 includes an antenna 101, a radio frequency device 102, a baseband device 103, a processor 104 and a memory 105. The antenna 101 is connected with the radio frequency device 102. In the uplink direction, the radio frequency device 102 receives information through the antenna 101, and sends the received information to the baseband device 103 for processing. In the downlink direction, the baseband device 103 processes the information to be sent and sends it to the radio frequency device 102, and the radio frequency device 102 processes the received information and sends it out through the antenna 101.

[0493] The method performed by the network side device in the above embodiment can be implemented in the baseband device 103, which includes a baseband processor.

[0494] The baseband device 103 can include at least one baseband board on which a plurality of chips are disposed, as shown in FIG. 10, one of which is a baseband processor, for example, connected to the memory 105 through a bus interface to invoke programs in the memory 105 to perform network device operations shown in the above method embodiments.

[0495] The network side device can further include a network interface 106, which is a common public radio interface (CPRI), for example.

[0496] Specifically, the network side device 100 of the embodiments of the present application further includes instructions or programs stored on the memory 105 and executable on the processor 104, and the processor 104 invokes the instructions or programs in the memory 105 to perform the methods executed by the modules shown in FIG. 6 or FIG. 7 and achieve the same technical effects, and thus details are not repeated here.

[0497] Specifically, the embodiments of the present application further provide a network side device. As shown in FIG. 11, the network side device 110 includes a processor 111, a network interface 112, and a memory 113. The network side device can be the indication device of AI model transmission shown in FIG. 6 or FIG. 7. The network interface 112 is a common public radio interface (CPRI), for example.

[0498] Specifically, the network side device 110 of the embodiments of the present application further includes instructions or programs stored on the memory 113 and executable on the processor 111, and the processor 111 invokes the instructions or programs in the memory 113 to perform the methods executed by the modules shown in FIG. 6 or FIG. 7 and achieve the same technical effects, and thus details are not repeated here.

[0499] The embodiments of the present application further provide a readable storage medium having programs or instructions stored thereon, which are executed by a processor to implement each process of the above AI model transmission indication method embodiments and achieve the same technical effects, and thus details are not repeated here.

[0500] The processor is the processor in the terminal 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.

[0501] The chip provided in the embodiments of the present application also can be called a system chip, a chip system, a system on chip, or the like.

[0502] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system chip, a chip system, a system on chip, or the like.

[0503] The embodiments of the present application further provide a computer program / program product stored in a storage medium, which is executed by at least one processor to implement the processes of the above-mentioned AI model transmission indication method embodiments and achieve the same technical effects. To avoid repetition, details are not described herein.

[0504] The embodiments of the present application further provide a wireless communication system, which includes a first communication device and a second communication device. The first communication device can be used to execute the steps of the AI model transmission indication method performed by the first communication device as described above. The second communication device can be used to execute the steps of the AI model transmission indication method performed by the second communication device as described above.

[0505] It should be noted that, in this document, the terms "comprising", "including", or any other variant thereof are intended to cover non-exclusive inclusions, so that processes, methods, articles, or devices that include a series of elements not only include those elements, but also include other elements not explicitly listed, or inherent to such processes, methods, articles, or devices. Without more limitations, the element defined by the statement "including a" does not exclude the presence of additional identical elements in the process, method, article, or device that includes the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to the order of performing functions as shown or discussed, but can also include performing functions in a substantially simultaneous manner or in reverse order, for example, the described method can be performed in an order different from that described, and various steps can also be added, omitted, or combined. In addition, the features described with reference to certain examples can be combined in other examples.

[0506] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be realized by means of computer software products and general hardware platforms, of course, they can also be realized by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disc, optical disc, etc.), and includes a plurality of instructions for making a terminal or network side device execute the method described in each embodiment of the present application.

[0507] 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.

Claims

1. An indication method of artificial intelligence (AI) model transmission, comprising: a first communication device sending first information, the first information indicating whether first model information of a target AI model needs to be received, or indicating a second communication device to determine whether the first model information of the target AI model needs to be sent; wherein the first information comprises at least one of: identification information of the target AI model; identification information of the first model information; identification information of second model information of the target AI model; timestamp information of the first model information; reception status information of the first model information; first indication information explicitly indicating whether the first model information of the target AI model needs to be received, or explicitly indicating the second communication device to determine whether the first model information of the target AI model needs to be sent; and second indication information indicating whether receiving the first model information is supported.

2. The method of claim 1, wherein: the first model information comprises at least one of: at least partial model structure and at least partial model parameter; the second model information comprises at least one of: at least partial model structure and at least partial model parameter; the first model information and the second model information are different.

3. The method of claim 1, wherein, the timestamp information comprises at least one of: update time; sending time; receiving time; valid time; training time; labeling time; release time.

4. The method of claim 1, wherein, the reception status information comprises at least one of: a first state indicating that the target AI model can be directly used, or indicating that the target AI model can be run, or indicating that the first model information has been received, or indicating that the first model information does not need to be received, or indicating that the second communication device does not need to send the first model information; a second state indicating that the first model information has not been received, or indicating that the second communication device needs to send the first model information; a third state indicating that the first model information has been received, but the second communication device needs to send the first model information; a fourth state indicating that the first model information has been received, but the second communication device needs to determine whether the first model information needs to be sent.

5. The method of claim 4, wherein: the first information comprises at least one of: identification information of the target AI model and identification information of the second model information, and reception status information of the first model information, the reception status information comprising one of the first state, the second state, the third state, and the fourth state; or, the first information comprises at least one of: identification information of the target AI model and identification information of the second model structure, and identification information of the first model information, and reception status information of the first model information, the reception status information comprising one of the first state, the third state, and the fourth state; or, The first information includes at least one of identification information of the target AI model and identification information of the second model structure, identification information of the first model information, and timestamp information of the first model information, and the first information is used to indicate that the receiving state information of the first model information is the fourth state.

6. The method of claim 4, wherein: The first information indicates that the receiving state information of the first model information is the first state through at least one of the following: identification information of the target AI model; identification information of the first model information; identification information of the second model information; Or, The first information indicates that the receiving state information of the first model information is the second state through at least one of the following: identification information of the target AI model; identification information of the second model information; Or, The first information indicates that the receiving state information of the first model information is the third state through at least one of the following: identification information of the target AI model; identification information of the first model information; identification information of the second model information; Or, The first information indicates that the receiving state information of the first model information is the fourth state through at least one of the following: identification information of the target AI model; identification information of the first model information; identification information of the second model information; timestamp information of the first model information.

7. The method of claim 1, further comprising: After the first communication device receives new first model information, determining whether previously received first model information is still available or unavailable.

8. The method of claim 7, wherein, After the first communication device receives new first model information, determining whether previously received first model information is still available or unavailable, includes: The first communication device receives third indication information, and the third indication information is used to indicate whether the previously received first model information is available after receiving the new first model information; The first communication device determines whether the previously received first model information is still available or unavailable after receiving the new first model information according to the third indication information; Or The first communication device determines whether the previously received first model information is still available or unavailable after receiving the new first model information according to a protocol agreement.

9. The method of claim 1 or 7 or 8, further comprising: After the first communication device receives new first model information, the first communication device sends fourth indication information, and the fourth indication information is used to indicate whether the first communication device previously received the first model information.

10. The method of claim 1, wherein, At least one of the content, format and rules of the first information is agreed by a protocol, offline or air interface interaction.

11. The method of claim 1, wherein, The target AI model includes at least one of the following: The first AI model used by the first communication device; The reference AI model of the first AI model; The second AI model, which is an AI model used by the first communication device or a test device in testing; The reference AI model of the second AI model; a third AI model, the third AI model being an AI model for the first communication device or test device to match the second AI model; a reference AI model of the third AI model.

12. The method of claim 1, wherein, the target AI model is used for one of: reference signal processing; channel signal transmission, reception, demodulation and / or sending; channel state information acquisition; beam management; channel prediction; channel and / or source coding and decoding; interference suppression; positioning; prediction and / or management of higher layer services and / or parameters; encoding and / or parsing of control signaling.

13. An indication method of AI model transmission, comprising: receiving, by a second communication device, first information indicating whether a first communication device needs to receive first model information of a target AI model, or indicating whether the second communication device needs to send the first model information of the target AI model; wherein the first information comprises at least one of: identification information of the target AI model; identification information of the first model information; identification information of second model information of the target AI model; timestamp information of the first model information; reception status information of the first model information; first indication information explicitly indicating whether the first model information of the target AI model needs to be received, or explicitly indicating whether the second communication device needs to send the first model information of the target AI model; second indication information indicating whether receiving the first model information is supported.

14. The method of claim 13, wherein: the first model information comprises at least one of: at least part of a model structure and at least part of a model parameter; the second model information comprises at least one of: at least part of a model structure and at least part of a model parameter; the first model information and the second model information are different.

15. The method of claim 13, wherein, the timestamp information comprises at least one of: update time; sending time; receiving time; valid time; training time; labeling time; release time.

16. The method of claim 13, wherein, the reception status information comprises at least one of: a first state indicating that the target AI model can be directly used, or indicating that the target AI model can be run, or indicating that the first model information has been received, or indicating that the first model information does not need to be received, or indicating that the second communication device does not need to send the first model information; a second state indicating that the first model information has not been received, or indicating that the second communication device needs to send the first model information; a third state indicating that the first model information has been received, but the second communication device needs to send the first model information; a fourth state indicating that the first model information has been received, but the second communication device needs to determine whether the first model information needs to be sent.

17. The method of claim 16, wherein: The first information includes at least one of identification information of the target AI model and identification information of the second model information, and reception state information of the first model information, the reception state information including one of the first state, the second state, the third state, and the fourth state. Or, The first information includes at least one of identification information of the target AI model and identification information of the second model structure, and identification information of the first model information, and reception state information of the first model information, the reception state information including one of the first state, the third state, and the fourth state. Or, The first information includes at least one of identification information of the target AI model and identification information of the second model structure, and identification information of the first model information, and timestamp information of the first model information, the first information indicating that the reception state information of the first model information is in the fourth state.

18. The method of claim 16, wherein: The first information indicates that the reception state information of the first model information is in the first state through at least one of the following: The identification information of the target AI model; The identification information of the first model information; The identification information of the second model information; Or, The first information indicates that the reception state information of the first model information is in the second state through at least one of the following: The identification information of the target AI model; The identification information of the second model information; Or, The first information indicates that the reception state information of the first model information is in the third state through at least one of the following: The identification information of the target AI model; The identification information of the first model information; The identification information of the second model information; Or, The first information indicates that the reception state information of the first model information is in the fourth state through at least one of the following: The identification information of the target AI model; The identification information of the first model information; The identification information of the second model information; The timestamp information of the first model information.

19. The method of claim 13, further comprising: The second communication device determines whether to send the first model information of the target AI model according to the first information.

20. The method of claim 13, further comprising: The second communication device sends third indication information, the third indication information indicating whether the first model information received before the first communication device receives new first model information is available.

21. The method of claim 13, further comprising: The second communication device receives fourth indication information, the fourth indication information indicating whether the first model information received before the first communication device receives new first model is available.

22. The method of claim 13, wherein, At least one of the content, format, and rule of the first information is agreed by a protocol, offline, or air interface interaction.

23. The method of claim 13, wherein, The target AI model includes at least one of: The first AI model used by the first communication device; a reference AI model of the first AI model; a second AI model, the second AI model being an AI model used by the first communication device or test device in testing; a reference AI model of the second AI model; a third AI model, the third AI model being an AI model used by the first communication device or test device to match the second AI model; a reference AI model of the third AI model.

24. The method of claim 13, wherein, The target AI model is used for one of the following: reference signal processing; channel signal transmission, reception, demodulation and / or sending; channel state information acquisition; beam management; channel prediction; channel and / or source coding and decoding; interference suppression; positioning; prediction and / or management of higher layer services and / or parameters; encoding and / or parsing of control signaling.

25. An indication device for AI model transmission, comprising: a sending module configured to send first information, the first information indicating whether first model information of a target AI model needs to be received, or indicating whether a second communication device needs to send the first model information of the target AI model; wherein the first information comprises at least one of the following: identification information of the target AI model; identification information of the first model information; identification information of second model information of the target AI model; timestamp information of the first model information; reception status information of the first model information; first indication information explicitly indicating whether the first model information of the target AI model needs to be received, or explicitly indicating whether the second communication device needs to send the first model information of the target AI model; second indication information indicating whether receiving the first model information is supported.

26. The device of claim 25, wherein: the first model information comprises at least one of the following: at least part of a model structure and at least part of a model parameter; the second model information comprises at least one of the following: at least part of a model structure and at least part of a model parameter; the first model information and the second model information are different.

27. The apparatus of claim 25, wherein, The reception status information comprises at least one of the following: a first state indicating that the target AI model can be directly used, or indicating that the target AI model can be run, or indicating that the first model information has been received, or indicating that the first model information does not need to be received, or indicating that the second communication device does not need to send the first model information; a second state indicating that the first model information has not been received, or indicating that the second communication device needs to send the first model information; a third state indicating that the first model information has been received, but the second communication device needs to send the first model information; a fourth state indicating that the first model information has been received, but the second communication device needs to determine whether the first model information needs to be sent.

28. The device of claim 25, further comprising: a processing module configured to determine whether previously received first model information is still available or not available after receiving new first model information.

29. The device of claim 28, wherein: The processing module is configured to receive third indication information, the third indication information being used to indicate whether the first model information received before the new first model information is available or not available; and determine, according to the third indication information, whether the first model information received before the new first model information is still available or not available after the new first model information is received. Or The processing module is configured to determine, according to a protocol agreement, whether the first model information received before the new first model information is still available or not available after the new first model information is received.

30. The apparatus of claim 25 or 28 or 29, wherein, The sending module is further configured to send fourth indication information after the new first model information is received, the fourth indication information being used to indicate whether the first model information received before by the first communication device is available or not available.

31. An indication device for AI model transmission, comprising: a receiving module configured to receive first information, the first information being used to indicate whether a first communication device needs to receive first model information of a target AI model, or to indicate whether a second communication device needs to send the first model information of the target AI model; wherein the first information comprises at least one of the following: identification information of the target AI model; identification information of the first model information; identification information of second model information of the target AI model; timestamp information of the first model information; reception state information of the first model information; first indication information, used to explicitly indicate whether the first model information of the target AI model needs to be received, or to explicitly indicate whether the second communication device needs to send the first model information of the target AI model; second indication information, used to indicate whether the first model information is supported to be received.

32. The device of claim 31, wherein: the first model information comprises at least one of the following: at least part of model structure and at least part of model parameters; the second model information comprises at least one of the following: at least part of model structure and at least part of model parameters; the first model information and the second model information are different.

33. The apparatus of claim 31, wherein, The reception state information comprises at least one of the following: a first state, indicating that the target AI model can be directly used, or indicating that the target AI model can be run, or indicating that the first model information has been received, or indicating that the first model information does not need to be received, or indicating that the second communication device does not need to send the first model information; a second state, indicating that the first model information has not been received, or indicating that the second communication device needs to send the first model information; a third state, indicating that the first model information has been received, but the second communication device needs to send the first model information; a fourth state, indicating that the first model information has been received, but the second communication device needs to determine whether the first model information needs to be sent. 34.A communication device comprising a processor and a memory, the memory storing programs or instructions executable on the processor, the programs or instructions, when executed by the processor, implement the steps of the indication method of AI model transmission according to any one of claims 1 to 12, or the programs or instructions, when executed by the processor, implement the steps of the indication method of AI model transmission according to any one of claims 13 to 24. 35.A readable storage medium, the readable storage medium storing programs or instructions, the programs or instructions, when executed by a processor, implement the indication method of AI model transmission according to any one of claims 1 to 12, or the programs or instructions, when executed by a processor, implement the indication method of AI model transmission according to any one of claims 13 to 24. 36.A chip comprising a processor and a communication interface, the communication interface and the processor being coupled, the processor being configured to execute programs or instructions to implement the indication method of AI model transmission according to any one of claims 1 to 12, or to implement the indication method of AI model transmission according to any one of claims 13 to 24. 37.A computer program product stored in a storage medium, the computer program product being executed by at least one processor to implement the indication method of AI model transmission according to any one of claims 1 to 12, or to implement the indication method of AI model transmission according to any one of claims 13 to 24.

Images