Ai model management method and apparatus, and communication device

Abstract

The present application belongs to the technical field of communications. Disclosed are an AI model management method and apparatus, and a communication device. The AI model management method in the embodiments of the present application comprises: a first communication device sending first information of a target AI model to a second communication device, wherein the first information comprises at least one of the following: a first identifier and a second identifier; and using a model identifier to indicate the target AI model, and performing model management of the target AI model, wherein the model identifier is associated with at least one of the first identifier and the second identifier. The first identifier is used for indicating the structure of the target AI model, and the second identifier is used for indicating a model parameter of the target AI model.

Description

AI model management methods, devices, and communication equipment

[0001] Cross-reference to related applications

[0002] This application claims priority to Chinese Patent Application No. 202411576486.3, filed in China on November 6, 2024, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application belongs to the field of communication technology, specifically relating to an AI model management method, apparatus, and communication equipment. Background Technology

[0004] Artificial intelligence (AI) has been widely applied in various fields. Integrating AI into wireless communication networks to significantly improve technical indicators such as throughput, latency, and user capacity is an important task for future wireless communication networks. AI modules can be implemented in various ways, such as neural networks, decision trees, support vector machines, and Bayesian classifiers.

[0005] Currently, for model transfer with a known model structure, there are two identifiers: the first identifier indicates the known model structure, and the second identifier indicates the model parameters to be transferred.

[0006] Although the model transmission has two identifiers, there is no reasonable and effective solution for the specific usage method and signaling process of the two identifiers, and the relationship with the AI ​​model's own identifier is not clear. How to use the model structure identifier and model parameter identifier for AI model management is an urgent problem to be solved. Summary of the Invention

[0007] This application provides an AI model management method, apparatus, and communication device, which can manage AI models using model structure identifiers and model parameter identifiers.

[0008] Firstly, an AI model management method is provided, including:

[0009] The first communication device sends first information of the target AI model to the second communication device, the first information including at least one of the following: a first identifier and a second identifier;

[0010] The first communication device uses a model identifier to indicate the target AI model and performs model management of the target AI model, wherein the model identifier is associated with at least one of the first identifier and the second identifier;

[0011] The first identifier is used to indicate the structure of the target AI model, and the second identifier is used to indicate the model parameters of the target AI model.

[0012] Secondly, an AI model management method is provided, including:

[0013] The second communication device receives first information about the target AI model sent by the first communication device, wherein the first information includes at least one of the following: a first identifier and / or a second identifier;

[0014] The second communication device uses a model identifier to indicate the target AI model and performs model management of the target AI model, wherein the model identifier is associated with at least one of the first identifier and the second identifier;

[0015] The first identifier is used to indicate the structure of the target AI model, and the second identifier is used to indicate the model parameters of the target AI model.

[0016] Thirdly, an AI model management device is provided, applied to a first communication device, including:

[0017] The first sending module is used to send first information of the target AI model to the second communication device, wherein the first information includes at least one of the following: a first identifier and a second identifier;

[0018] A first processing module is configured to use a model identifier to indicate the target AI model and perform model management of the target AI model, wherein the model identifier is associated with at least one of the first identifier and the second identifier;

[0019] The first identifier is used to indicate the structure of the target AI model, and the second identifier is used to indicate the model parameters of the target AI model.

[0020] Fourthly, an AI model management device is provided, applied to a second communication device, comprising:

[0021] The first receiving module is configured to receive first information of the target AI model sent by the first communication device, wherein the first information includes at least one of the following: a first identifier and / or a second identifier;

[0022] The third processing module is used to use a model identifier to indicate the target AI model and to perform model management of the target AI model, wherein the model identifier is associated with at least one of the first identifier and the second identifier;

[0023] The first identifier is used to indicate the structure of the target AI model, and the second identifier is used to indicate the model parameters of the target AI model.

[0024] Fifthly, an AI model management apparatus is provided, the apparatus being configured to perform the steps of the method described in the first aspect, or to implement the steps of the method described in the second aspect.

[0025] In a sixth aspect, a communication device is provided, which is a first communication device, comprising a processor and a memory, the memory storing a program or instructions executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the method described in the first aspect.

[0026] In a seventh aspect, a communication device is provided, which is a first communication device including a processor and a communication interface, wherein the communication interface is used to send first information of a target AI model to a second communication device, the first information including at least one of the following: a first identifier and a second identifier;

[0027] The first identifier is used to indicate the structure of the target AI model, and the second identifier is used to indicate the model parameters of the target AI model.

[0028] Eighthly, a communication device is provided, which is a second communication device, the communication device including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as described in the second aspect.

[0029] Ninth aspect, a communication device is provided, which is a second communication device, including a processor and a communication interface, wherein the communication interface is used to receive first information of a target AI model sent by a first communication device, the first information including at least one of the following: a first identifier and / or a second identifier;

[0030] The first identifier is used to indicate the structure of the target AI model, and the second identifier is used to indicate the model parameters of the target AI model.

[0031] In a tenth aspect, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect, or implement the steps of the method described in the second aspect.

[0032] Eleventhly, a wireless communication system is provided, comprising: a first communication device and a second communication device, wherein the first communication device is configured to perform the steps of the method described in the first aspect, and the second communication device is configured to perform the steps of the method described in the second aspect.

[0033] In a twelfth aspect, a chip is provided, the chip including a processor and a communication interface coupled to the processor, the processor being configured to run programs or instructions to implement the method as described in the first aspect, or to implement the method as described in the second aspect.

[0034] In a thirteenth aspect, a computer program / program product is provided, which is stored in a storage medium and executed by at least one processor to implement the steps of the AI ​​model management method as described in the first or second aspect.

[0035] In this embodiment of the application, by sending a first identifier indicating the structure of the target AI model or a second identifier indicating the model parameters of the target AI model to a second communication device, and then managing the target AI model based on the model identifier associated with at least one of the first and second identifiers, it is possible to indicate the model identifier of the target AI model based on the model structure identifier or the model parameter identifier, thereby realizing the management of the AI ​​model using the model structure identifier and the model parameter identifier. Attached Figure Description

[0036] Figure 1 is a block diagram of a wireless communication system applicable to an embodiment of this application;

[0037] Figure 2 is a schematic diagram of the neuron's structure;

[0038] Figure 3 is one of the flowcharts of the AI ​​model management method according to an embodiment of this application;

[0039] Figure 4 is a second flowchart illustrating the AI ​​model management method according to an embodiment of this application;

[0040] Figure 5 is a schematic diagram of one of the modules of the AI ​​model management device according to an embodiment of this application;

[0041] Figure 6 is a second schematic diagram of the modules of the AI ​​model management device according to an embodiment of this application;

[0042] Figure 7 is a schematic diagram of the structure of a communication device according to an embodiment of this application;

[0043] Figure 8 is a schematic diagram of the structure of the terminal according to an embodiment of this application;

[0044] Figure 9 is a schematic diagram of the structure of the access network device according to an embodiment of this application. Detailed Implementation

[0045] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0046] 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.

[0047] 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.

[0048] It is worth noting that the technologies described in this application are not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA), or other systems. The terms "system" and "network" in this application are often used interchangeably, and the described technologies can be used in the systems and radio technologies mentioned above, as well as in other systems and radio technologies. The following description describes New Radio (NR) systems for illustrative purposes, and the term NR is used in most of the following description; however, these technologies can also be applied to systems other than NR systems, such as 6th Generation (6G) communication systems.

[0049] Figure 1 shows a block diagram of a wireless communication system applicable to an embodiment of this application. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 can be a mobile phone, tablet computer, laptop computer, notebook computer, personal digital assistant (PDA), handheld computer, netbook, ultra-mobile personal computer (UMPC), mobile internet device (MID), augmented reality (AR), virtual reality (VR) device, robot, wearable device, flight vehicle, vehicle user equipment (VUE), shipboard equipment, pedestrian user equipment (PUE), smart home (home devices with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), game console, personal computer (PC), ATM, or self-service machine, etc. Wearable devices include: smartwatches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart chains, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among these, in-vehicle devices can also be referred to as in-vehicle terminals, in-vehicle controllers, in-vehicle modules, in-vehicle components, in-vehicle chips, or in-vehicle units, etc. It should be noted that the specific type of terminal 11 is not limited in this application embodiment. Network-side equipment 12 may include access network equipment or core network equipment, wherein access network equipment may also be referred to as Radio Access Network (RAN) equipment, radio access network function, or radio access network unit. Access network equipment may include base stations, Wireless Local Area Network (WLAN) access points (APs), or Wireless Fidelity (WiFi) nodes, etc.The term "base station" can be referred to as Node B (NB), Evolved Node B (eNB), Next Generation Node B (gNB), New Radio Node B (NR Node B), Access Point, Relay Base Station (RBS), Serving Base Station (SBS), Base Transceiver Station (BTS), Radio Base Station, Radio Transceiver, Basic Service Set (BSS), Extended Service Set (ESS), Home Node B (HNB), Home Evolved Node B, Transmit / Receive Point (TRP), or any other suitable term in the relevant field, as long as the same technical effect is achieved. The term "base station" is not limited to any specific technical terminology. It should be noted that this application embodiment only uses a base station in an NR system as an example for description and does not limit the specific type of base station.

[0050] Core network equipment, also known as core network nodes, core network functions, or core network elements, includes, but is not limited to, at least one of the following: Mobility Management Entity (MME), Access and Mobility Management Function (AMF), Session Management Function (SMF), User Plane Function (UPF), Policy Control Function (PCF), Policy and Charging Rules Function (PCRF), Edge Application Server Discovery Function (EASDF), Unified Data Management (UDM), Unified Data Repository (UDR), Home Subscriber Server (HSS), Centralized network configuration (CNC), Network Repository Function (NRF), Network Exposure Function (NEF), Local NEF (or L-NEF), and Binding Support. The core network functions include: BSF (Block Network Function), Application Function (AF), Location Management Function (LMF), Gateway Mobile Location Centre (GMLC), and Network Data Analytics Function (NWDAF). It should be noted that this application embodiment only uses core network equipment in the NR system as an example and does not limit the specific type of core network equipment. If the name of the core network equipment mentioned in this application embodiment changes in subsequent protocol versions (e.g., 6G), it will still be within the scope of protection of this application.

[0051] Optionally, the core network equipment can be implemented by one or more functional modules in a single device, or by multiple devices working together; this application does not specifically limit this. It is understood that the aforementioned functional modules can be network elements in hardware devices, software functional modules running on dedicated hardware, or virtualized functional modules instantiated on a platform (e.g., a cloud platform).

[0052] The relevant technologies associated with the embodiments of this application will be described below.

[0053] A neural network is composed of neurons, and a schematic diagram of a neuron is shown in Figure 2. Where a1, a2, ... a K The input is w, where w is the weight (multiplicative coefficient), b is the bias (additive coefficient), and σ(.) is the activation function. Common activation functions include Sigmoid, tanh, and ReLU (Rectified Linear Unit).

[0054] The parameters of a neural network are optimized using gradient optimization algorithms. Gradient optimization algorithms are a class of algorithms that minimize or maximize an objective function (sometimes called a loss function), which is often a mathematical combination of model parameters and data. For example, given data X and its corresponding label Y, we construct a neural network model f(.). With the model, we can obtain the predicted output f(x) based on the input x, and calculate the difference between the predicted value and the true value (f(x) - Y), which is the loss function. Our goal is to find suitable W and b that minimize the value of the above loss function. The smaller the loss value, the closer our model is to the reality.

[0055] Most common optimization algorithms are based on the error back propagation (BP) algorithm. The basic idea of ​​the BP algorithm is that the learning process consists of two stages: forward propagation of the signal and backward propagation of the error. During forward propagation, the input sample is introduced from the input layer, processed layer by layer by the hidden layers, and then propagated to the output layer. If the actual output of the output layer does not match the expected output, the process transitions to the error back propagation stage. Error back propagation involves propagating the output error back to the input layer layer by layer through the hidden layers, distributing the error to all units in each layer, thus obtaining the error signal of each unit. This error signal serves as the basis for adjusting the weights of each unit. This process of adjusting the weights through forward and backward propagation is cyclical. This continuous adjustment of weights is the learning and training process of the network. This process continues until the error of the network output is reduced to an acceptable level, or until the predetermined number of learning iterations is reached.

[0056] Common optimization algorithms include gradient descent, stochastic gradient descent (SGD), mini-batch gradient descent, momentum method, Nesterov (stochastic gradient descent with momentum), adaptive gradient descent (Adagrad), Adadelta, root mean square prop (RMSprop), and adaptive momentum estimation (Adam).

[0057] During error backpropagation, these optimization algorithms calculate the gradient based on the error / loss obtained from the loss function with respect to the current neuron, add the learning rate, previous gradients / derivatives / partial derivatives, etc., and then pass the gradient to the previous layer.

[0058] The AI ​​model mentioned in this application embodiment may also be referred to as an AI unit, ML (machine learning) model, ML unit, AI structure, AI function, AI characteristic, machine learning model, neural network, neural network function, neural network functionality, etc. Alternatively, the AI ​​model may refer to a processing unit capable of implementing specific algorithms, formulas, characteristics, processing flows, capabilities, etc., related to AI. Or, the AI ​​model may be a processing method, algorithm, function, characteristic, module, or unit for a specific dataset. Alternatively, the AI ​​model may be a processing method, algorithm, function, characteristic, module, or unit running on AI / ML related hardware such as a Graphics Processing Unit (GPU), Neural Processing Unit (NPU), Tensor Processing Unit (TPU), or Application-Specific Integrated Circuit (ASIC). This application embodiment does not specifically limit the specific meaning of these terms. Optionally, the specific dataset includes the input and / or output of the AI ​​model.

[0059] Optionally, the identifier of the AI ​​model may be an AI model identifier, an AI structure identifier, an AI algorithm identifier, or an identifier of a specific dataset associated with the AI ​​model, or an identifier of a specific scenario, environment, region, cell, channel characteristics, or device related to the AI / ML, or an identifier of a function, feature, capability, or module related to the AI / ML. In this embodiment, no specific limitation is made in this regard.

[0060] The AI ​​model management method, apparatus, and communication device provided in this application will be described in detail below with reference to the accompanying drawings and through some embodiments and application scenarios.

[0061] As shown in Figure 3, this application embodiment provides an AI model management method, including:

[0062] Step 301: The first communication device sends the first information of the target AI model to the second communication device, wherein the first information includes at least one of the following: a first identifier and a second identifier;

[0063] Wherein, the first identifier is used to indicate the structure of the target AI model, and optionally, the first identifier can be understood as a model structure identifier; the second identifier is used to indicate the model parameters of the target AI model, and optionally, the second identifier can be understood as a model parameter identifier.

[0064] Step 302: The first communication device uses a model identifier to indicate the target AI model and performs model management of the target AI model, wherein the model identifier is associated with at least one of the first identifier and the second identifier;

[0065] It should be noted that, in this embodiment of the application, a first identifier indicating the structure of the target AI model or a second identifier indicating the model parameters of the target AI model is sent to a second communication device, and then the target AI model is managed based on the model identifier associated with at least one of the first and second identifiers. In this way, the model identifier of the target AI model can be indicated based on the model structure identifier or the model parameter identifier, thereby realizing the management of the AI ​​model using the model structure identifier and the model parameter identifier.

[0066] Optionally, the first information may also include specific model structure information or specific model parameter information. For example, the model parameter information may refer to specific parameters on the model neurons, such as multiplicative coefficients, additive coefficients, etc., or to the parameters of the activation function.

[0067] Optionally, in one implementation, the target AI model includes at least one of the following:

[0068] A11. The first AI model used by the first communication device or the second communication device;

[0069] A12. The reference AI model for the first AI model;

[0070] A13. The second AI model used in the test by the first communication device, the second communication device, or the test device;

[0071] A14. The reference AI model for the second AI model;

[0072] A15. The first communication device, the second communication device, or the test device is used to match the third AI model of the second AI model used in the test.

[0073] It should be noted that this feature is mainly for two-way communication use cases (such as Channel State Information (CSI) compression and recovery, encoding and decoding, etc.).

[0074] A16. The reference AI model of the third AI model.

[0075] Optionally, in one implementation, the target AI model is used to achieve at least one of the following:

[0076] A101, Reference Signal Processing;

[0077] Optionally, the reference signal processing may include signal detection, filtering, equalization, etc.

[0078] Optionally, the reference signal may include, but is not limited to, at least one of the following: demodulation reference signal (DMRS), sounding reference signal (SRS), synchronization signal / physical broadcast channel signal block (or synchronization signal block) (SSB), channel state information reference signal (CSI-RS), tracking reference signal (TRS), positioning reference signal (PRS), phase-tracking reference signal (PTRS), etc.

[0079] A102, Channel signal transmission;

[0080] A103, Channel signal reception;

[0081] A104, Channel signal demodulation;

[0082] A105, Channel signal transmission;

[0083] Optionally, the channel signal includes, but is not limited to, at least one of the following: Physical downlink control channel (PDCCH), Physical downlink shared channel (PDSCH), Physical uplink control channel (PUCCH), Physical uplink shared channel (PUSCH), Physical random-access channel (PRACH), Physical broadcast channel (PBCH), etc.

[0084] A106. Channel state information acquisition;

[0085] Alternatively, this situation may include at least one of the following:

[0086] a) Channel state information feedback, the main contents of which may include channel-related information, channel matrix-related information, channel characteristic information, channel matrix characteristic information, precoding matrix indicator (PMI), rank indicator (RI), CSI-RS resource indicator (CRI), channel quality indicator (CQI), layer indicator (LI), etc.

[0087] b) Frequency Division Duplex (FDD) uplink and downlink reciprocity. For FDD systems, based on partial reciprocity, the access network equipment obtains angle and delay information from the uplink channel. It can notify the terminal of the angle and delay information through CSI-RS precoding or direct indication. The terminal reports the information according to the instructions of the access network equipment or selects and reports within the range indicated by the access network equipment, thereby reducing the computational load on the terminal and the overhead of CSI reporting.

[0088] A107, Beam Management;

[0089] Optionally, the beam management may include, but is not limited to, at least one of the following: beam measurement, beam reporting, beam prediction (spatial domain prediction or frequency domain prediction), beam failure detection, beam failure recovery, and new beam indication during beam failure recovery.

[0090] A108, Channel Prediction;

[0091] Optionally, the channel prediction may include, but is not limited to, at least one of the following: prediction of channel state information and beam prediction.

[0092] A109, Channel encoding and decoding;

[0093] Optionally, the channel encoding and decoding may include: channel coding, channel decoding, joint source channel coding, and joint source channel decoding.

[0094] A110, Source encoding and decoding;

[0095] Optionally, the source encoding and decoding may include: source encoding, source decoding, joint source-channel encoding, and joint source-channel decoding.

[0096] A111, Interference Suppression;

[0097] Optionally, the interference mentioned in this case may include, but is not limited to, at least one of the following: intra-cell interference, inter-cell interference, out-of-band interference, and intermodulation interference.

[0098] A112, Positioning;

[0099] Optionally, positioning in this case can be understood as: the specific location (including horizontal and / or vertical position) or possible future trajectory of the terminal estimated by reference signal (e.g., SRS), or information for auxiliary position estimation or trajectory estimation, such as time of arrival (TOA), line-of-sight or non-line-of-sight, or reference signal time difference (RSTD).

[0100] A113, Forecasting of high-level business or high-level parameters;

[0101] A114. Management of high-level business or high-level parameters;

[0102] Optionally, the high-level services or high-level parameters mentioned in the embodiments of this application may include, but are not limited to, at least one of the following: throughput, required data packet size, service requirements, moving speed, and noise information.

[0103] A115. Analysis of control signaling;

[0104] Optionally, the control signaling may include power control related signaling, beam management related signaling, etc.

[0105] It should be noted that A101-A114 above can be understood as the functions that the target AI model can achieve.

[0106] Optionally, in one implementation, the model management includes at least one of the following:

[0107] Model activation, model deactivation, model switching, model selection, model rollback (e.g., rolling back to a non-AI mode / module / algorithm), model monitoring (e.g., performance testing), model identification, model registration, model transfer, and model-related data collection.

[0108] Optionally, the model identifier is sent from the second communication device to the first communication device to indicate at least the first identifier or the second identifier; or

[0109] The model identifier includes at least a first identifier or a second identifier.

[0110] This can be understood as follows: In one scenario, the model identifier is determined by the second communication device through at least one of the first and second identifiers. The model identifier is used to indicate at least the first or second identifier. That is, in this case, the second communication device associates at least one of the first and second identifiers with the model identifier. After association, the second communication device also needs to feed back the model identifier to the first communication device so that the first and second communication devices have the same understanding of the model identifier, ensuring that both can accurately manage the model. Further, optionally, the model identifier is also used to indicate at least one of the following: version information of the model or model parameters, timestamp, cell identifier, cell group identifier, region identifier, public land mobile network (PLMN) identifier, vendor identifier of the first communication device, model identifier of the first communication device, vendor identifier of the second communication device, and model identifier of the second communication device.

[0111] In another scenario, the first communication device identifies at least one of the first identifier and the second identifier as the model identifier. That is, the model identifier may include not only one of the first and second identifiers but also other information. The second communication device shares the same understanding as the first communication device, and upon receiving the first identifier and / or the second identifier, also identifies at least one of the first and / or the second identifier as the model identifier. In this case, the two devices no longer transmit the actual model identifier, but instead use at least one of the first and second identifiers as the model identifier. That is, the model identifier includes at least one of the first and second identifiers (or can be understood as including but not limited to at least one of the first and second identifiers). Further optionally, the model identifier may also include at least one of the following: version information of the model or model parameters, a timestamp, a cell identifier, a cell group identifier, a region identifier, a PLMN identifier, the supplier identifier of the first communication device, the model identifier of the first communication device, the supplier identifier of the second communication device, and the model identifier of the second communication device.

[0112] Optionally, in one implementation, the first identifier is a global identifier; or

[0113] The first identifier is obtained by at least one of the following:

[0114] B11. Agreement stipulations;

[0115] B12, Manufacturer's offline agreement;

[0116] In this case, it can be understood that the first identifier is an offline agreement between the manufacturers of the first and second communication devices.

[0117] B13. Determined based on allocation or instruction from a second communication device;

[0118] Optionally, in one scenario of this approach: the first communication device reports model structure information, and then the second communication device assigns or indicates a first identifier to the first communication device based on the model structure information reported by the first communication device; in another scenario: the second communication device directly indicates at least one model structure information and its corresponding first identifier. This can be understood as the second communication device sending the correspondence between the model structure information and the first identifier information to the first communication device, and the first communication device determining the first identifier to be sent based on the model structure of the model to be used.

[0119] Optionally, in one implementation, the first identifier includes N1 identifiers, and the first communication device supports activating, running, or using models corresponding to N2 first identifiers;

[0120] Where N2 is greater than or equal to 1, and N1 is greater than or equal to N2.

[0121] This situation can be understood as follows: the first communication device can report N1 first identifiers, but the first communication device only supports activating, running or using the models corresponding to N2 first identifiers at the same time. The second communication device should also follow this rule, that is, the second communication device can only activate the models corresponding to N2 first identifiers at the same time, or the second communication device can only send the model parameters of the models corresponding to N2 first identifiers at the same time.

[0122] Optionally, in one implementation, the second identifier is a global identifier or a local identifier; or

[0123] The second identifier is obtained through at least one of the following:

[0124] C11, Manufacturer's offline agreement;

[0125] This situation can be understood as the second identifier being an offline agreement between the manufacturers of the first and second communication devices.

[0126] C12. Determined based on allocation or instruction from a second communication device;

[0127] Optionally, in one scenario of this approach: the first communication device reports model parameter information, and then the second communication device assigns or indicates a second identifier to the first communication device based on the model structure information reported by the first communication device; in another scenario: the second communication device directly indicates at least one model parameter information and its corresponding second identifier. This can be understood as the second communication device sending the correspondence between the model parameter information and the second identifier information to the first communication device, and the first communication device determining the second identifier to be sent based on the model parameters of the model to be used.

[0128] Optionally, in one implementation, if the second identifier is available at least in the current cell, the cell group to which the current cell is located, or the region to which the current cell is located, or if the second identifier is a global identifier, then the second identifier or the first information does not carry the target identifier;

[0129] The target identifier includes at least one of the following: cell identifier, cell group identifier, and region identifier.

[0130] This situation can be understood as follows: if the second identifier is a global identifier or the second identifier does not restrict its scope of use, then in order to reduce signaling overhead, the first communication device does not need to carry the scope of application information of the second identifier when reporting. After receiving the information sent by the first communication device, the second communication device can know that the second identifier is a global identifier.

[0131] Optionally, in one implementation, if the second identifier is a local identifier, or the second identifier is used for a first region or a second region, then the second identifier or the first information carries the target identifier, or the second identifier indicates the target identifier;

[0132] The target identifier includes at least one of the following: cell identifier, cell group identifier, and region identifier; the first region is the region corresponding to the target identifier, and the second region is a region that has at least one of the same wireless environment characteristics, software configuration, and hardware configuration as the first region.

[0133] This situation can be understood as follows: if the second identifier is a local identifier or the second identifier has limitations on its scope of use, in order for the second communication device to clearly know the scope of use of the second identifier, the first communication device needs to carry a target identifier indicating the scope of application of the second identifier when reporting.

[0134] Alternatively, at least one of the following can be used when transferring model parameters:

[0135] Scenario 1: Different model parameters corresponding to the same model structure have different first identifiers.

[0136] This situation can be understood as follows: for the same model structure, the first identifier corresponding to the transmission of all model parameters is different from the first identifier corresponding to the transmission of different parts of the model parameters. For example, for the same model structure, the first identifier corresponding to the transmission of all model parameters is ID1_1, the first identifier corresponding to the transmission of one part of the model parameters is ID1_2, and the first identifier corresponding to the transmission of another part of the model parameters is ID1_3. Then ID1_1, ID1_2, and ID1_3 are all different.

[0137] Case 2: The first identifier is the same for the same model structure, and the second identifier is used to indicate whether all model parameters are transmitted or only some model parameters are transmitted.

[0138] This situation can be understood as follows: for the same model structure, the same first identifier is used, but different second identifiers indicate whether all model parameters are transmitted or only some model parameters are transmitted (for example, at least some information of the second identifier can be used to indicate whether all model parameters are transmitted or only some model parameters are transmitted). For example, for the same model structure, corresponding to the first identifier ID1, the second identifier corresponding to the transmission of all model parameters is ID2_1, the second identifier corresponding to one type of transmission of partial model parameters is ID2_2, and the second identifier corresponding to another type of transmission of partial model parameters is ID2_3. In this case, ID2_1, ID2_2, and ID2_3 are all different.

[0139] Scenario 3: The first information also includes: indication information, which is used to indicate the transmission of all model parameters or the transmission of some model parameters;

[0140] This situation can be understood as using the same first identifier for the same model structure, but requiring additional indication information to indicate whether all model parameters are transmitted or only some model parameters are transmitted. For example, for the same model structure, corresponding to the first identifier ID1, the indication information for transmitting all model parameters is ID3_1, the indication information for transmitting one type of partial model parameters is ID3_2, and the indication information for transmitting another type of partial model parameters is ID3_3. In this case, ID3_1, ID3_2, and ID3_3 are all different.

[0141] Scenario 4: The first communication device determines, based on the received model parameters of the target AI model, whether the target AI model is transmitting all model parameters or only some model parameters.

[0142] Alternatively, this situation can be understood as follows: when transmitting AI model parameters, it is not indicated whether all model parameters or only some model parameters are transmitted. Instead, the specific transmission method, whether to transmit all or only some model parameters, is determined by the model parameters received by the first communication device.

[0143] Optionally, in one implementation, determining whether the target AI model requires transmission of all or part of its model parameters based on the received model parameters of the target AI model includes:

[0144] Based on the second information, it is determined that the target AI model involves the transmission of all model parameters or a partial transmission of model parameters.

[0145] The second information includes at least one of the following:

[0146] The size of the model parameters, the overhead of the model parameters, the payload of the model parameters, and the content contained in the model parameters.

[0147] Optionally, in one implementation, the content included in the model parameters may include, but is not limited to, the variable names, identifiers, contents, and parameters of neurons, layers, partial model parameters, and partial model structures; for example, if the transmitted model parameters only include the variable names, identifiers, contents, and parameters of partial neurons, layers, partial model parameters, and partial model structures, then it can be determined that it is a partial model parameter transmission.

[0148] Optionally, in one implementation, if the target AI model has only one model structure, the first information includes only the second identifier.

[0149] This situation can be understood as follows: if the model structure of the target AI model on the first communication device side is different from the model structure of other AI models, then the first communication device can report only the second identifier instead of the first identifier to the second communication device, thereby saving signaling overhead.

[0150] For example, this situation may include at least one of the following:

[0151] For a given AI function, AI use case, or AI feature, the first communication device can only report or support one model structure.

[0152] For a specific AI function, AI use case, or AI feature, the protocol stipulates only one model structure.

[0153] For a given AI function, AI use case, or AI feature, there is only one offline agreed-upon model structure.

[0154] For a given AI function, AI use case, or AI feature, the second communication device indicates or supports only one model structure.

[0155] Optionally, the first communication device mentioned in the embodiments of this application can be a terminal, an access network device, or a core network device, and the second communication device can be a terminal, an access network device, or a core network device; for example, the first communication device is a terminal and the second communication device is an access network device, or, for example, the first communication device is a core network device and the second communication device is an access network device; it should be noted that the combination of the first communication device and the second communication device in the embodiments of this application is merely an example and does not constitute a limitation on the scope of protection of this application.

[0156] It should be noted that the embodiments of this application have determined the detailed schemes for model structure identification and model parameter identification, as well as the schemes for their use in AI model lifecycle management, which is conducive to better AI model management in AI communication.

[0157] As shown in Figure 4, this application embodiment provides an AI model management method, including:

[0158] Step 401: The second communication device receives first information of the target AI model sent by the first communication device, wherein the first information includes at least one of the following: a first identifier and / or a second identifier;

[0159] Step 402: The second communication device uses a model identifier to indicate the target AI model and performs model management of the target AI model, wherein the model identifier is associated with at least one of the first identifier and the second identifier;

[0160] The first identifier is used to indicate the structure of the target AI model, and the second identifier is used to indicate the model parameters of the target AI model.

[0161] Optionally, the model identifier is used to indicate at least a first identifier or a second identifier; or

[0162] The model identifier includes at least a first identifier or a second identifier.

[0163] Optionally, if the model identifier is used to indicate at least the first identifier or the second identifier, the method further includes:

[0164] The second communication device determines the model identifier of the target AI model based on the first information;

[0165] The second communication device sends the model identifier of the target AI model to the first communication device.

[0166] Optionally, the model identifier may also be used to indicate, or the model identifier may include at least one of the following:

[0167] Version information of the model or model parameters, timestamp, cell identifier, cell group identifier, region identifier, public land mobile network (PLMN) identifier, supplier identifier of the first communication device, model identifier of the first communication device, supplier identifier of the second communication device, and model identifier of the second communication device.

[0168] Optionally, the first identifier is a global identifier; or

[0169] The second identifier can be a global identifier or a local identifier.

[0170] Optionally, the first identifier includes N1 identifiers, and the second communication device only supports activating the models corresponding to the N2 first identifiers or only supports sending the model parameters of the models corresponding to the N2 first identifiers to the first communication device;

[0171] Where N2 is greater than or equal to 1, and N1 is greater than or equal to N2.

[0172] Optionally, it also includes:

[0173] If the second identifier or the first information does not carry a target identifier, it is determined that the second identifier is available at least in the current cell, the cell group to which the current cell is located, or the region to which the current cell is located, or it is determined that the second identifier is a global identifier;

[0174] The target identifier includes at least one of the following: cell identifier, cell group identifier, and region identifier.

[0175] Optionally, the method further includes:

[0176] If the second identifier or the first information carries a target identifier, or the second identifier indicates a target identifier, then the second identifier is determined to be a local identifier, or the second identifier is used for a first region or a second region;

[0177] The target identifier includes at least one of the following: cell identifier, cell group identifier, and region identifier; the first region is the region corresponding to the target identifier, and the second region is a region that has the same wireless environment characteristics, software configuration, and / or hardware configuration as the first region.

[0178] Optionally, the first identifiers corresponding to different model parameter transmissions for the same model structure are different; or

[0179] The same model structure has the same first identifier, and the second identifier is used to indicate whether all model parameters are transferred or only some model parameters are transferred; or

[0180] The first information also includes: indication information, which is used to indicate the transmission of all model parameters or a portion of the model parameters.

[0181] Optionally, if the target AI model has only one model structure, the first information includes only the second identifier.

[0182] Optionally, the target AI model includes at least one of the following:

[0183] The first AI model used by the first communication device or the second communication device;

[0184] The reference AI model for the first AI model;

[0185] The second AI model used in the test by the first communication device, the second communication device, or the test device;

[0186] The reference AI model for the second AI model;

[0187] The first communication device, the second communication device, or the test device is used to match the third AI model of the second AI model used in the test;

[0188] The reference AI model for the third AI model.

[0189] Optionally, the target AI model is used to achieve at least one of the following:

[0190] Reference signal processing;

[0191] Channel signal transmission;

[0192] Channel signal reception;

[0193] Channel signal demodulation;

[0194] Channel signal transmission;

[0195] Channel state information acquisition;

[0196] Beam management;

[0197] Channel prediction;

[0198] Channel encoding and decoding;

[0199] Source encoding / decoding;

[0200] Interference suppression;

[0201] position;

[0202] Forecasting of high-level business or high-level parameters;

[0203] Management of high-level business operations or high-level parameters;

[0204] Parsing control signaling.

[0205] It should be noted that all descriptions of the second communication device side in the above embodiments are applicable to the embodiments of the AI ​​model management method applied to the second communication device side, and can achieve the same technical effect, so they will not be repeated here.

[0206] This application provides an AI model management device. As an example, the AI ​​model management device can be a communication device or a component within a communication device, such as a chip. The communication device can be a terminal, a network-side device, or a server, etc. Exemplarily, the terminal can be, but is not limited to, the type of terminal 11 listed above, and the network-side device can be, but is not limited to, the type of network-side device 12 listed above. This application does not impose specific limitations.

[0207] The AI ​​model management device includes a receiving module, a transmitting module, and a processing module. These modules can be implemented in software or hardware. When implemented in hardware, the processing module can be implemented by a processor. For example, the processor can include general-purpose processors, special-purpose processors, such as a Central Processing Unit (CPU), microprocessor, Digital Signal Processor (DSP), Artificial Intelligence (AI) processor, Graphics Processing Unit (GPU), Application Specific Integrated Circuit (ASIC), Network Processor (NP), Field Programmable Gate Array (FPGA), or other programmable logic devices, gate circuits, transistors, discrete hardware components, etc. The receiving and transmitting modules can be implemented by a communication interface, which can include one or more of the following: transceiver, pins, circuits, bus, radio frequency unit, etc.

[0208] Specifically, referring to Figure 5, when the AI ​​model management device is a first communication device or a component of the first communication device, the AI ​​model management device 500 includes:

[0209] The first sending module 501 is used to send first information of the target AI model to the second communication device, the first information including at least one of the following: a first identifier and a second identifier;

[0210] The first processing module 502 is used to indicate the target AI model using a model identifier and to perform model management of the target AI model, wherein the model identifier is associated with at least one of the first identifier and the second identifier;

[0211] The first identifier is used to indicate the structure of the target AI model, and the second identifier is used to indicate the model parameters of the target AI model.

[0212] Optionally, the model identifier is sent from the second communication device to the first communication device to indicate at least the first identifier or the second identifier; or

[0213] The model identifier includes at least a first identifier or a second identifier.

[0214] Optionally, the model identifier may also be used to indicate, or the model identifier may include at least one of the following:

[0215] Version information of the model or model parameters, timestamp, cell identifier, cell group identifier, region identifier, public land mobile network (PLMN) identifier, supplier identifier of the first communication device, model identifier of the first communication device, supplier identifier of the second communication device, and model identifier of the second communication device.

[0216] Optionally, the first identifier is a global identifier; or

[0217] The first identifier is obtained by at least one of the following:

[0218] The agreement stipulates;

[0219] Manufacturer offline agreement;

[0220] Determined based on allocation or instruction from the second communication device.

[0221] Optionally, the first identifier includes N1 identifiers, and the first communication device supports activating, running, or using models corresponding to N2 first identifiers;

[0222] Where N2 is greater than or equal to 1, and N1 is greater than or equal to N2.

[0223] Optionally, the second identifier is a global identifier or a local identifier; or

[0224] The second identifier is obtained through at least one of the following:

[0225] Manufacturer offline agreement;

[0226] Determined based on allocation or instruction from the second communication device.

[0227] Optionally, if the second identifier is available at least in the current cell, the cell group to which the current cell is located, or the region to which the current cell is located, or if the second identifier is a global identifier, then the second identifier or the first information does not carry the target identifier;

[0228] The target identifier includes at least one of the following: cell identifier, cell group identifier, and region identifier.

[0229] Optionally, if the second identifier is a local identifier, or the second identifier is used for a first region or a second region, then the second identifier or the first information carries the target identifier, or the second identifier indicates the target identifier;

[0230] The target identifier includes at least one of the following: cell identifier, cell group identifier, and region identifier; the first region is the region corresponding to the target identifier, and the second region is a region that has at least one of the same wireless environment characteristics, software configuration, and hardware configuration as the first region.

[0231] Optionally, the first identifiers corresponding to different model parameter transmissions for the same model structure are different; or

[0232] The same model structure has the same first identifier, and the second identifier is used to indicate whether all model parameters are transferred or only some model parameters are transferred; or

[0233] The first information also includes: indication information, which is used to indicate the transmission of all model parameters or a portion of the model parameters; or

[0234] The device further includes:

[0235] The second processing module is used to determine whether the target AI model is to transmit all model parameters or only some model parameters based on the received model parameters of the target AI model.

[0236] Optionally, the second processing module is used for:

[0237] Based on the second information, it is determined that the target AI model involves the transmission of all model parameters or a partial transmission of model parameters.

[0238] The second information includes at least one of the following:

[0239] The size of the model parameters, the cost of the model parameters, the load of the model parameters, and the contents contained in the model parameters.

[0240] Optionally, if the target AI model has only one model structure, the first information includes only the second identifier.

[0241] Optionally, the target AI model includes at least one of the following:

[0242] The first AI model used by the first communication device or the second communication device;

[0243] The reference AI model for the first AI model;

[0244] The second AI model used in the test by the first communication device, the second communication device, or the test device;

[0245] The reference AI model for the second AI model;

[0246] The first communication device, the second communication device, or the test device is used to match the third AI model of the second AI model used in the test;

[0247] The reference AI model for the third AI model.

[0248] Optionally, the target AI model is used to achieve at least one of the following:

[0249] Reference signal processing;

[0250] Channel signal transmission;

[0251] Channel signal reception;

[0252] Channel signal demodulation;

[0253] Channel signal transmission;

[0254] Channel state information acquisition;

[0255] Beam management;

[0256] Channel prediction;

[0257] Channel encoding and decoding;

[0258] Source encoding / decoding;

[0259] Interference suppression;

[0260] position;

[0261] Forecasting of high-level business or high-level parameters;

[0262] Management of high-level business operations or high-level parameters;

[0263] Parsing control signaling.

[0264] The AI ​​model management device provided in this application embodiment can implement the various processes implemented in the method embodiment of FIG3 and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0265] Referring to Figure 6, when the AI ​​model management device is a second communication device or a component of a second communication device, the AI ​​model management device 600 includes:

[0266] The first receiving module 601 is configured to receive first information of a target AI model sent by a first communication device, wherein the first information includes at least one of the following: a first identifier and / or a second identifier;

[0267] The third processing module 602 is used to indicate the target AI model using a model identifier and to perform model management of the target AI model, wherein the model identifier is associated with at least one of the first identifier and the second identifier;

[0268] The first identifier is used to indicate the structure of the target AI model, and the second identifier is used to indicate the model parameters of the target AI model.

[0269] Optionally, in the device, the model identifier is used to indicate at least a first identifier or a second identifier; or

[0270] The model identifier includes at least a first identifier or a second identifier.

[0271] Optionally, if the model identifier is used to indicate at least the first identifier or the second identifier, the device further includes:

[0272] The fourth processing module is used to determine the model identifier of the target AI model based on the first information;

[0273] The second sending module is used to send the model identifier of the target AI model to the first communication device.

[0274] Optionally, the model identifier may also be used to indicate, or the model identifier may include at least one of the following:

[0275] Version information of the model or model parameters, timestamp, cell identifier, cell group identifier, region identifier, public land mobile network (PLMN) identifier, supplier identifier of the first communication device, model identifier of the first communication device, supplier identifier of the second communication device, and model identifier of the second communication device.

[0276] Optionally, the first identifier is a global identifier; or

[0277] The second identifier can be a global identifier or a local identifier.

[0278] Optionally, the first identifier includes N1 identifiers, and the second communication device only supports activating the models corresponding to the N2 first identifiers or only supports sending the model parameters of the models corresponding to the N2 first identifiers to the first communication device;

[0279] Where N2 is greater than or equal to 1, and N1 is greater than or equal to N2.

[0280] Optionally, the device further includes:

[0281] The fifth processing module is used to determine, if the second identifier or the first information does not carry a target identifier, that the second identifier is available at least in the current cell, the cell group to which the current cell is located, or the region to which the current cell is located, or to determine that the second identifier is a global identifier;

[0282] The target identifier includes at least one of the following: cell identifier, cell group identifier, and region identifier.

[0283] Optionally, the device further includes:

[0284] The sixth processing module is configured to determine that the second identifier is a local identifier or the second identifier is used for a first region or a second region if the second identifier or the first information carries a target identifier or the second identifier indicates a target identifier;

[0285] The target identifier includes at least one of the following: cell identifier, cell group identifier, and region identifier; the first region is the region corresponding to the target identifier, and the second region is a region that has the same wireless environment characteristics, software configuration, and / or hardware configuration as the first region.

[0286] Optionally, the first identifiers corresponding to different model parameter transmissions for the same model structure are different; or

[0287] The same model structure has the same first identifier, and the second identifier is used to indicate whether all model parameters are transferred or only some model parameters are transferred; or

[0288] The first information also includes: indication information, which is used to indicate the transmission of all model parameters or a portion of the model parameters.

[0289] Optionally, if the target AI model has only one model structure, the first information includes only the second identifier.

[0290] Optionally, the target AI model includes at least one of the following:

[0291] The first AI model used by the first communication device or the second communication device;

[0292] The reference AI model for the first AI model;

[0293] The second AI model used in the test by the first communication device, the second communication device, or the test device;

[0294] The reference AI model for the second AI model;

[0295] The first communication device, the second communication device, or the test device is used to match the third AI model of the second AI model used in the test;

[0296] The reference AI model for the third AI model.

[0297] Optionally, the target AI model is used to achieve at least one of the following:

[0298] Reference signal processing;

[0299] Channel signal transmission;

[0300] Channel signal reception;

[0301] Channel signal demodulation;

[0302] Channel signal transmission;

[0303] Channel state information acquisition;

[0304] Beam management;

[0305] Channel prediction;

[0306] Channel encoding and decoding;

[0307] Source encoding / decoding;

[0308] Interference suppression;

[0309] position;

[0310] Forecasting of high-level business or high-level parameters;

[0311] Management of high-level business operations or high-level parameters;

[0312] Parsing control signaling.

[0313] The AI ​​model management device provided in this application embodiment can implement the various processes implemented in the method embodiment of FIG4 and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0314] Optionally, as shown in FIG7, this application embodiment also provides a communication device 700, including a processor 701 and a memory 702. The memory 702 stores a program or instructions that can be executed by the processor 701. For example, when the communication device 700 is a first communication device, when the program or instructions are executed by the processor 701, they implement the various steps of the above-described AI model management method embodiment and achieve the same technical effect. When the communication device 700 is a second communication device, when the program or instructions are executed by the processor 701, they implement the various steps of the above-described AI model management method embodiment and achieve the same technical effect. To avoid repetition, further details are omitted here.

[0315] Preferably, this application embodiment also provides a communication device, which is a terminal, including a processor, a memory, and a program or instructions stored in the memory and executable on the processor. When the program or instructions are executed by the processor, they implement the various processes of the above-described communication processing method embodiment and achieve the same technical effect. The terminal may be the AI ​​model management device shown in FIG5. Specifically, FIG8 is a schematic diagram of the hardware structure of a terminal implementing an embodiment of this application.

[0316] The terminal 800 includes, but is not limited to, at least some of the following components: radio frequency unit 801, network module 802, audio output unit 803, input unit 804, sensor 805, display unit 806, user input unit 807, interface unit 808, memory 809, and processor 810.

[0317] Those skilled in the art will understand that the terminal 800 may also include a power supply (such as a battery) for powering various components. The power supply can be logically connected to the processor 810 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The terminal structure shown in Figure 8 does not constitute a limitation on the terminal. The terminal may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0318] It should be understood that, in this embodiment, the input unit 804 may include a graphics processor 8041 and a microphone 8042. The graphics processor 8041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 806 may include a display panel 8061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like. The user input unit 807 includes at least one of a touch panel 8071 and other input devices 8072. The touch panel 8071 is also called a touch screen. The touch panel 8071 may include two parts: a touch detection device and a touch controller. Other input devices 8072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, and joysticks, which will not be described in detail here.

[0319] In this embodiment, after receiving downlink data from the access network device, the radio frequency unit 801 can transmit it to the processor 810 for processing; in addition, the radio frequency unit 801 can send uplink data to the network-side device. Typically, the radio frequency unit 801 includes, but is not limited to, antennas, amplifiers, transceivers, couplers, low-noise amplifiers, duplexers, etc.

[0320] The memory 809 can be used to store software programs or instructions, as well as various data. The memory 809 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 809 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 809 in the embodiments of this application includes, but is not limited to, these and any other suitable types of memory.

[0321] Processor 810 may include one or more processing units; optionally, processor 810 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into processor 810.

[0322] The radio frequency unit 801 is used to: send first information of the target AI model to the second communication device, wherein the first information includes at least one of the following: a first identifier and a second identifier;

[0323] The processor 810 is configured to: use a model identifier to indicate the target AI model, and perform model management of the target AI model, wherein the model identifier is associated with at least one of the first identifier and the second identifier;

[0324] The first identifier is used to indicate the structure of the target AI model, and the second identifier is used to indicate the model parameters of the target AI model.

[0325] Optionally, the model identifier is sent from the second communication device to the first communication device to indicate at least the first identifier or the second identifier; or

[0326] The model identifier includes at least a first identifier or a second identifier.

[0327] Optionally, the model identifier may also be used to indicate, or the model identifier may include at least one of the following:

[0328] Version information of the model or model parameters, timestamp, cell identifier, cell group identifier, region identifier, public land mobile network (PLMN) identifier, supplier identifier of the first communication device, model identifier of the first communication device, supplier identifier of the second communication device, and model identifier of the second communication device.

[0329] Optionally, the first identifier is a global identifier; or

[0330] The first identifier is obtained by at least one of the following:

[0331] The agreement stipulates;

[0332] Manufacturer offline agreement;

[0333] Determined based on allocation or instruction from the second communication device.

[0334] Optionally, the first identifier includes N1 identifiers, and the first communication device supports activating, running, or using models corresponding to N2 first identifiers;

[0335] Where N2 is greater than or equal to 1, and N1 is greater than or equal to N2.

[0336] Optionally, the second identifier is a global identifier or a local identifier; or

[0337] The second identifier is obtained through at least one of the following:

[0338] Manufacturer offline agreement;

[0339] Determined based on allocation or instruction from the second communication device.

[0340] Optionally, if the second identifier is available at least in the current cell, the cell group to which the current cell is located, or the region to which the current cell is located, or if the second identifier is a global identifier, then the second identifier or the first information does not carry the target identifier;

[0341] The target identifier includes at least one of the following: cell identifier, cell group identifier, and region identifier.

[0342] Optionally, if the second identifier is a local identifier, or the second identifier is used for a first region or a second region, then the second identifier or the first information carries the target identifier, or the second identifier indicates the target identifier;

[0343] The target identifier includes at least one of the following: cell identifier, cell group identifier, and region identifier; the first region is the region corresponding to the target identifier, and the second region is a region that has at least one of the same wireless environment characteristics, software configuration, and hardware configuration as the first region.

[0344] Optionally, the first identifiers corresponding to different model parameter transmissions for the same model structure are different; or

[0345] The same model structure has the same first identifier, and the second identifier is used to indicate whether all model parameters are transferred or only some model parameters are transferred; or

[0346] The first information also includes: indication information, which is used to indicate the transmission of all model parameters or a portion of the model parameters; or

[0347] The processor 810 is also used for:

[0348] Based on the received model parameters of the target AI model, it is determined whether the target AI model is transmitting all model parameters or only some model parameters.

[0349] Optionally, the processor 810 is configured to:

[0350] Based on the second information, it is determined that the target AI model involves the transmission of all model parameters or a partial transmission of model parameters.

[0351] The second information includes at least one of the following:

[0352] The size of the model parameters, the cost of the model parameters, the load of the model parameters, and the contents contained in the model parameters.

[0353] Optionally, if the target AI model has only one model structure, the first information includes only the second identifier.

[0354] Optionally, the target AI model includes at least one of the following:

[0355] The first AI model used by the first communication device or the second communication device;

[0356] The reference AI model for the first AI model;

[0357] The second AI model used in the test by the first communication device, the second communication device, or the test device;

[0358] The reference AI model for the second AI model;

[0359] The first communication device, the second communication device, or the test device is used to match the third AI model of the second AI model used in the test;

[0360] The reference AI model for the third AI model.

[0361] Optionally, the target AI model is used to achieve at least one of the following:

[0362] Reference signal processing;

[0363] Channel signal transmission;

[0364] Channel signal reception;

[0365] Channel signal demodulation;

[0366] Channel signal transmission;

[0367] Channel state information acquisition;

[0368] Beam management;

[0369] Channel prediction;

[0370] Channel encoding and decoding;

[0371] Source encoding / decoding;

[0372] Interference suppression;

[0373] position;

[0374] Forecasting of high-level business or high-level parameters;

[0375] Management of high-level business operations or high-level parameters;

[0376] Parsing control signaling.

[0377] This application embodiment also provides a communication device, which is a first communication device, including a processor and a communication interface. The communication interface is used to send first information of a target AI model to a second communication device. The first information includes at least one of the following: a first identifier and a second identifier.

[0378] The processor is configured to: use a model identifier to indicate the target AI model, and perform model management of the target AI model, wherein the model identifier is associated with at least one of the first identifier and the second identifier;

[0379] The first identifier is used to indicate the structure of the target AI model, and the second identifier is used to indicate the model parameters of the target AI model.

[0380] Optionally, the model identifier is sent from the second communication device to the first communication device to indicate at least the first identifier or the second identifier; or

[0381] The model identifier includes at least a first identifier or a second identifier.

[0382] Optionally, the model identifier may also be used to indicate, or the model identifier may include at least one of the following:

[0383] Version information of the model or model parameters, timestamp, cell identifier, cell group identifier, region identifier, public land mobile network (PLMN) identifier, supplier identifier of the first communication device, model identifier of the first communication device, supplier identifier of the second communication device, and model identifier of the second communication device.

[0384] Optionally, the first identifier is a global identifier; or

[0385] The first identifier is obtained by at least one of the following:

[0386] The agreement stipulates;

[0387] Manufacturer offline agreement;

[0388] Determined based on allocation or instruction from the second communication device.

[0389] Optionally, the first identifier includes N1 identifiers, and the first communication device supports activating, running, or using models corresponding to N2 first identifiers;

[0390] Where N2 is greater than or equal to 1, and N1 is greater than or equal to N2.

[0391] Optionally, the second identifier is a global identifier or a local identifier; or

[0392] The second identifier is obtained through at least one of the following:

[0393] Manufacturer offline agreement;

[0394] Determined based on allocation or instruction from the second communication device.

[0395] Optionally, if the second identifier is available at least in the current cell, the cell group to which the current cell is located, or the region to which the current cell is located, or if the second identifier is a global identifier, then the second identifier or the first information does not carry the target identifier;

[0396] The target identifier includes at least one of the following: cell identifier, cell group identifier, and region identifier.

[0397] Optionally, if the second identifier is a local identifier, or the second identifier is used for a first region or a second region, then the second identifier or the first information carries the target identifier, or the second identifier indicates the target identifier;

[0398] The target identifier includes at least one of the following: cell identifier, cell group identifier, and region identifier; the first region is the region corresponding to the target identifier, and the second region is a region that has at least one of the same wireless environment characteristics, software configuration, and hardware configuration as the first region.

[0399] Optionally, the first identifiers corresponding to different model parameter transmissions for the same model structure are different; or

[0400] The same model structure has the same first identifier, and the second identifier is used to indicate whether all model parameters are transferred or only some model parameters are transferred; or

[0401] The first information also includes: indication information, which is used to indicate the transmission of all model parameters or a portion of the model parameters; or

[0402] The processor is also used for:

[0403] Based on the received model parameters of the target AI model, it is determined whether the target AI model is transmitting all model parameters or only some model parameters.

[0404] Optionally, the processor is configured to:

[0405] Based on the second information, it is determined that the target AI model involves the transmission of all model parameters or a partial transmission of model parameters.

[0406] The second information includes at least one of the following:

[0407] The size of the model parameters, the cost of the model parameters, the load of the model parameters, and the contents contained in the model parameters.

[0408] Optionally, if the target AI model has only one model structure, the first information includes only the second identifier.

[0409] Optionally, the target AI model includes at least one of the following:

[0410] The first AI model used by the first communication device or the second communication device;

[0411] The reference AI model for the first AI model;

[0412] The second AI model used in the test by the first communication device, the second communication device, or the test device;

[0413] The reference AI model for the second AI model;

[0414] The first communication device, the second communication device, or the test device is used to match the third AI model of the second AI model used in the test;

[0415] The reference AI model for the third AI model.

[0416] Optionally, the target AI model is used to achieve at least one of the following:

[0417] Reference signal processing;

[0418] Channel signal transmission;

[0419] Channel signal reception;

[0420] Channel signal demodulation;

[0421] Channel signal transmission;

[0422] Channel state information acquisition;

[0423] Beam management;

[0424] Channel prediction;

[0425] Channel encoding and decoding;

[0426] Source encoding / decoding;

[0427] Interference suppression;

[0428] position;

[0429] Forecasting of high-level business or high-level parameters;

[0430] Management of high-level business operations or high-level parameters;

[0431] Parsing control signaling.

[0432] Specifically, this application embodiment also provides a communication device, which is an access network device, and the access network device can be the AI ​​model management device shown in FIG6. As shown in FIG9, the access network device 900 includes: an antenna 901, a radio frequency device 902, a baseband device 903, a processor 904, and a memory 905. The antenna 901 is connected to the radio frequency device 902. In the uplink direction, the radio frequency device 902 receives information through the antenna 901 and sends the received information to the baseband device 903 for processing. In the downlink direction, the baseband device 903 processes the information to be transmitted and sends it to the radio frequency device 902, and the radio frequency device 902 processes the received information and transmits it through the antenna 901.

[0433] The method executed by the network-side device in the above embodiments can be implemented in the baseband device 903, which includes a baseband processor.

[0434] The baseband device 903 may include at least one baseband board, on which multiple chips are disposed, as shown in FIG9. One of the chips is, for example, a baseband processor, which is connected to the memory 905 via a bus interface to call the program in the memory 905 and execute the network device operation shown in the above method embodiment.

[0435] The communication device may also include a network interface 906, such as a common public radio interface (CPRI).

[0436] Specifically, the access network device 900 in this application embodiment further includes: instructions or programs stored in memory 905 and executable on processor 904. Processor 904 calls the instructions or programs in memory 905 to execute the methods executed by each module shown in FIG6 and achieve the same technical effect. To avoid repetition, it will not be described in detail here.

[0437] This application embodiment also provides a communication device, which is a second communication device, including a processor and a communication interface. The communication interface is used to receive first information of a target AI model sent by a first communication device. The first information includes at least one of the following: a first identifier and / or a second identifier.

[0438] The processor is configured to: use a model identifier to indicate the target AI model, and perform model management of the target AI model, wherein the model identifier is associated with at least one of the first identifier and the second identifier;

[0439] The first identifier is used to indicate the structure of the target AI model, and the second identifier is used to indicate the model parameters of the target AI model.

[0440] Optionally, the model identifier is used to indicate at least a first identifier or a second identifier; or

[0441] The model identifier includes at least a first identifier or a second identifier.

[0442] Optionally, if the model identifier is used to indicate at least the first identifier or the second identifier, the processor is further configured to: determine the model identifier of the target AI model based on the first information;

[0443] The communication interface is also used to: send the model identifier of the target AI model to the first communication device.

[0444] Optionally, the model identifier may also be used to indicate, or the model identifier may include at least one of the following:

[0445] Version information of the model or model parameters, timestamp, cell identifier, cell group identifier, region identifier, public land mobile network (PLMN) identifier, supplier identifier of the first communication device, model identifier of the first communication device, supplier identifier of the second communication device, and model identifier of the second communication device.

[0446] Optionally, the first identifier is a global identifier; or

[0447] The second identifier can be a global identifier or a local identifier.

[0448] Optionally, the first identifier includes N1 identifiers, and the second communication device only supports activating the models corresponding to the N2 first identifiers or only supports sending the model parameters of the models corresponding to the N2 first identifiers to the first communication device;

[0449] Where N2 is greater than or equal to 1, and N1 is greater than or equal to N2.

[0450] Optionally, the processor is further configured to:

[0451] If the second identifier or the first information does not carry a target identifier, it is determined that the second identifier is available at least in the current cell, the cell group to which the current cell is located, or the region to which the current cell is located, or it is determined that the second identifier is a global identifier;

[0452] The target identifier includes at least one of the following: cell identifier, cell group identifier, and region identifier.

[0453] Optionally, the processor is further configured to:

[0454] If the second identifier or the first information carries a target identifier, or the second identifier indicates a target identifier, then the second identifier is determined to be a local identifier, or the second identifier is used for a first region or a second region;

[0455] The target identifier includes at least one of the following: cell identifier, cell group identifier, and region identifier; the first region is the region corresponding to the target identifier, and the second region is a region that has the same wireless environment characteristics, software configuration, and / or hardware configuration as the first region.

[0456] Optionally, the first identifiers corresponding to different model parameter transmissions for the same model structure are different; or

[0457] The same model structure has the same first identifier, and the second identifier is used to indicate whether all model parameters are transferred or only some model parameters are transferred; or

[0458] The first information also includes: indication information, which is used to indicate the transmission of all model parameters or a portion of the model parameters.

[0459] Optionally, if the target AI model has only one model structure, the first information includes only the second identifier.

[0460] Optionally, the target AI model includes at least one of the following:

[0461] The first AI model used by the first communication device or the second communication device;

[0462] The reference AI model for the first AI model;

[0463] The second AI model used in the test by the first communication device, the second communication device, or the test device;

[0464] The reference AI model for the second AI model;

[0465] The first communication device, the second communication device, or the test device is used to match the third AI model of the second AI model used in the test;

[0466] The reference AI model for the third AI model.

[0467] Optionally, the target AI model is used to achieve at least one of the following:

[0468] Reference signal processing;

[0469] Channel signal transmission;

[0470] Channel signal reception;

[0471] Channel signal demodulation;

[0472] Channel signal transmission;

[0473] Channel state information acquisition;

[0474] Beam management;

[0475] Channel prediction;

[0476] Channel encoding and decoding;

[0477] Source encoding / decoding;

[0478] Interference suppression;

[0479] position;

[0480] Forecasting of high-level business or high-level parameters;

[0481] Management of high-level business operations or high-level parameters;

[0482] Parsing control signaling.

[0483] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described AI model management method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0484] The processor mentioned above is the processor in the terminal or access network device described in the above embodiments. The readable storage medium can be non-volatile or non-transient. The readable storage medium can include computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0485] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described AI model management method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0486] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0487] This application also provides a computer program / program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the above-described AI model management method embodiments, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0488] This application also provides a communication system, including: a first communication device and a second communication device, wherein the first communication device can be used to execute the steps of the above-described AI model management method, and the second communication device can be used to execute the steps of the above-described AI model management method.

[0489] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0490] From the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of computer software products plus necessary general-purpose hardware platforms, and of course, they can also be implemented by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes several instructions to cause the terminal or network-side device to execute the methods described in the various embodiments of this application.

[0491] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other implementations under the guidance of this application without departing from the spirit and scope of the claims. All of these implementations are within the protection scope of this application.

Claims

1. An artificial intelligence (AI) model management method, comprising: The first communication device sends first information of the target AI model to the second communication device, the first information including at least one of the following: a first identifier and a second identifier; The first communication device uses a model identifier to indicate the target AI model and performs model management of the target AI model, wherein the model identifier is associated with at least one of the first identifier and the second identifier; The first identifier is used to indicate the structure of the target AI model, and the second identifier is used to indicate the model parameters of the target AI model.

2. The method according to claim 1, wherein, The model identifier is sent from the second communication device to the first communication device to indicate at least the first identifier or the second identifier; or The model identifier includes at least a first identifier or a second identifier.

3. The method according to claim 2, wherein, The model identifier is also used to indicate, or the model identifier includes at least one of the following: Version information of the model or model parameters, timestamp, cell identifier, cell group identifier, region identifier, public land mobile network (PLMN) identifier, supplier identifier of the first communication device, model identifier of the first communication device, supplier identifier of the second communication device, and model identifier of the second communication device.

4. The method according to claim 1, wherein, The first identifier is a global identifier; or The first identifier is obtained by at least one of the following: The agreement stipulates; Manufacturer offline agreement; Determined based on allocation or instruction from the second communication device.

5. The method according to claim 1, wherein, The first identifier includes N1 identifiers, and the first communication device supports activating, running, or using models corresponding to N2 first identifiers; Where N2 is greater than or equal to 1, and N1 is greater than or equal to N2.

6. The method according to claim 1, wherein, The second identifier is either a global identifier or a local identifier; or The second identifier is obtained through at least one of the following: Manufacturer offline agreement; Determined based on allocation or instruction from the second communication device.

7. The method according to claim 1 or 6, wherein, If the second identifier is available at least in the current cell, the cell group to which the current cell is located, or the region to which the current cell is located, or if the second identifier is a global identifier, then the second identifier or the first information does not carry the target identifier; The target identifier includes at least one of the following: cell identifier, cell group identifier, and region identifier.

8. The method according to claim 1 or 6, wherein, If the second identifier is a local identifier, or the second identifier is used for a first region or a second region, then the second identifier or the first information carries the target identifier, or the second identifier indicates the target identifier; The target identifier includes at least one of the following: cell identifier, cell group identifier, and region identifier; the first region is the region corresponding to the target identifier, and the second region is a region that has at least one of the same wireless environment characteristics, software configuration, and hardware configuration as the first region.

9. The method according to claim 1, wherein, The first identifiers for different model parameter transmissions corresponding to the same model structure are different; or The first identifier is the same for the same model structure, and the second identifier is used to indicate whether all model parameters are transmitted or only some model parameters are transmitted. or The first information also includes: indication information, which is used to indicate the transmission of all model parameters or a portion of the model parameters; or The method further includes: Based on the received model parameters of the target AI model, it is determined whether the target AI model is transmitting all model parameters or only some model parameters.

10. The method according to claim 9, wherein, The step of determining whether the target AI model requires transmission of all or part of its model parameters based on the received model parameters of the target AI model includes: Based on the second information, it is determined that the target AI model involves the transmission of all model parameters or a partial transmission of model parameters. The second information includes at least one of the following: The size of the model parameters, the cost of the model parameters, the load of the model parameters, and the contents contained in the model parameters.

11. The method according to claim 1, wherein, When the target AI model has only one model structure, the first information includes only the second identifier.

12. The method according to any one of claims 1-11, wherein, The target AI model includes at least one of the following: The first AI model used by the first communication device or the second communication device; The reference AI model for the first AI model; The second AI model used in the test by the first communication device, the second communication device, or the test device; The reference AI model for the second AI model; The first communication device, the second communication device, or the test device is used to match the third AI model of the second AI model used in the test; The reference AI model for the third AI model.

13. The method according to any one of claims 1-12, wherein, The target AI model is used to achieve at least one of the following: Reference signal processing; Channel signal transmission; Channel signal reception; Channel signal demodulation; Channel signal transmission; Channel state information acquisition; Beam management; Channel prediction; Channel encoding and decoding; Source encoding / decoding; Interference suppression; position; Forecasting of high-level business or high-level parameters; Management of high-level business operations or high-level parameters; Parsing control signaling.

14. An AI model management method, comprising: The second communication device receives first information about the target AI model sent by the first communication device, wherein the first information includes at least one of the following: a first identifier and / or a second identifier; The second communication device uses a model identifier to indicate the target AI model and performs model management of the target AI model, wherein the model identifier is associated with at least one of the first identifier and the second identifier; The first identifier is used to indicate the structure of the target AI model, and the second identifier is used to indicate the model parameters of the target AI model.

15. The method according to claim 14, wherein, The model identifier is used to indicate at least the first identifier or the second identifier; or The model identifier includes at least a first identifier or a second identifier.

16. The method according to claim 15, wherein, When the model identifier is used to indicate at least the first identifier or the second identifier, the method further includes: The second communication device determines the model identifier of the target AI model based on the first information; The second communication device sends the model identifier of the target AI model to the first communication device.

17. The method according to claim 15, wherein, The model identifier is also used to indicate, or the model identifier includes at least one of the following: Version information of the model or model parameters, timestamp, cell identifier, cell group identifier, region identifier, public land mobile network (PLMN) identifier, supplier identifier of the first communication device, model identifier of the first communication device, supplier identifier of the second communication device, and model identifier of the second communication device.

18. The method according to claim 14, wherein, The first identifier is a global identifier; or The second identifier can be a global identifier or a local identifier.

19. The method of claim 14, wherein, The first identifier includes N1 identifiers, and the second communication device only supports activating the models corresponding to the N2 first identifiers or only supports sending the model parameters of the models corresponding to the N2 first identifiers to the first communication device; Where N2 is greater than or equal to 1, and N1 is greater than or equal to N2.

20. The method of claim 14, wherein, Also includes: If the second identifier or the first information does not carry a target identifier, it is determined that the second identifier is available at least in the current cell, the cell group to which the current cell is located, or the region to which the current cell is located, or it is determined that the second identifier is a global identifier; The target identifier includes at least one of the following: cell identifier, cell group identifier, and region identifier.

21. The method according to claim 14, wherein, Also includes: If the second identifier or the first information carries a target identifier, or the second identifier indicates a target identifier, then the second identifier is determined to be a local identifier, or the second identifier is used for a first region or a second region; The target identifier includes at least one of the following: cell identifier, cell group identifier, and region identifier; the first region is the region corresponding to the target identifier, and the second region is a region that has the same wireless environment characteristics, software configuration, and / or hardware configuration as the first region.

22. The method according to claim 14, wherein, The first identifiers for different model parameter transmissions corresponding to the same model structure are different; or The first identifier is the same for the same model structure, and the second identifier is used to indicate whether all model parameters are transmitted or only some model parameters are transmitted. or The first information also includes: indication information, which is used to indicate the transmission of all model parameters or a portion of the model parameters.

23. The method according to claim 14, wherein, When the target AI model has only one model structure, the first information includes only the second identifier.

24. An artificial intelligence (AI) model management device, applied to a first communication device, the device comprising: The first sending module is used to send first information of the target AI model to the second communication device, wherein the first information includes at least one of the following: a first identifier and a second identifier; A first processing module is configured to use a model identifier to indicate the target AI model and perform model management of the target AI model, wherein the model identifier is associated with at least one of the first identifier and the second identifier; The first identifier is used to indicate the structure of the target AI model, and the second identifier is used to indicate the model parameters of the target AI model.

25. The apparatus according to claim 24, wherein, The model identifier is sent from the second communication device to the first communication device to indicate at least the first identifier or the second identifier; or The model identifier includes at least a first identifier or a second identifier.

26. The apparatus according to claim 24, wherein, The first identifier includes N1 identifiers, and the first communication device supports activating, running, or using models corresponding to N2 first identifiers; Where N2 is greater than or equal to 1, and N1 is greater than or equal to N2.

27. The apparatus according to claim 24, wherein, If the second identifier is available at least in the current cell, the cell group to which the current cell is located, or the region to which the current cell is located, or if the second identifier is a global identifier, then the second identifier or the first information does not carry the target identifier; The target identifier includes at least one of the following: cell identifier, cell group identifier, and region identifier.

28. The apparatus according to claim 24, wherein, If the second identifier is a local identifier, or the second identifier is used for a first region or a second region, then the second identifier or the first information carries the target identifier, or the second identifier indicates the target identifier; The target identifier includes at least one of the following: cell identifier, cell group identifier, and region identifier; the first region is the region corresponding to the target identifier, and the second region is a region that has at least one of the same wireless environment characteristics, software configuration, and hardware configuration as the first region.

29. The apparatus according to claim 24, wherein, The first identifiers for different model parameter transmissions corresponding to the same model structure are different; or The first identifier is the same for the same model structure, and the second identifier is used to indicate whether all model parameters are transmitted or only some model parameters are transmitted. or The first information also includes: indication information, which is used to indicate the transmission of all model parameters or a portion of the model parameters; or The device further includes: The second processing module is used to determine whether the target AI model is to transmit all model parameters or only some model parameters based on the received model parameters of the target AI model.

30. A communication device, the communication device being a first communication device, the communication device comprising a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the AI ​​model management method as described in any one of claims 1 to 13.

31. An AI model management device, applied to a second communication device, the device comprising: The first receiving module is configured to receive first information of the target AI model sent by the first communication device, wherein the first information includes at least one of the following: a first identifier and / or a second identifier; The third processing module is used to use a model identifier to indicate the target AI model and to perform model management of the target AI model, wherein the model identifier is associated with at least one of the first identifier and the second identifier; The first identifier is used to indicate the structure of the target AI model, and the second identifier is used to indicate the model parameters of the target AI model.

32. The apparatus according to claim 31, wherein, The model identifier is used to indicate at least the first identifier or the second identifier; or The model identifier includes at least a first identifier or a second identifier.

33. The apparatus according to claim 32, wherein, When the model identifier is used to indicate at least the first identifier or the second identifier, the device further includes: The fourth processing module is used to determine the model identifier of the target AI model based on the first information; The second sending module is used to send the model identifier of the target AI model to the first communication device.

34. A communication device, the communication device being a second communication device, the communication device comprising a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the AI ​​model management method as described in any one of claims 14 to 23.

35. A readable storage medium storing a program or instructions that, when executed by a processor, implement the steps of the AI ​​model management method as described in any one of claims 1-23.

36. A computer program product comprising computer instructions that, when executed by a processor, implement the steps of the method as claimed in any one of claims 1 to 23.

Images