Model switching method and related device

Abstract

The invention provides a model switching method and a related device, which can avoid downloading a complete AI model when switching a network coverage area or a task each time, and is beneficial to reducing signaling overhead. The method comprises the steps that an AI model is determined, the AI model comprises multiple levels of sub-models, and each level of sub-model in the multiple levels of sub-models is suitable for at least one object; obtaining an identifier of the target object; based on the identifier of the target object, determining a target sub-model of a hierarchy corresponding to the target object; and switching the sub-model of the level corresponding to the target object in the multi-level sub-model into the target sub-model.

Description

Technical Field

[0001] This application relates to the field of communications, and in particular, to a model switching method and related apparatus. Background Art

[0002] In a communication device, a processing module based on an artificial intelligence (AI) model can be trained through data driving, and can optimize modules such as channel coding, modulation, and waveform in the physical layer, as well as functions such as upper-layer beam management, channel state information (CSI) compression, and positioning according to scenarios, so as to achieve better transmission signal design and reception performance.

[0003] Currently, different AI models may correspond to different network coverage areas or tasks (for example, positioning tasks, beam prediction tasks), and a network device can train an AI model for a specific network coverage area and a specific task. A terminal can download a trained AI model from the network device. When the terminal moves and causes a change in the network coverage area, or when the task changes, the terminal needs to download an AI model applicable to the switched network coverage area or task from the network device side.

[0004] However, each time the network coverage area or task is switched, downloading a complete AI model from the network device side will bring a large signaling overhead. Summary of the Invention

[0005] This application provides a model switching method and related apparatus, which can avoid downloading a complete AI model each time the network coverage area or task is switched, and is beneficial to reducing signaling overhead.

[0006] In a first aspect, a model switching method is provided. This method can be executed by a first communication device, which can be a terminal or a network device, or a component (such as a processor, a chip, or a chip system, etc.) configured in the terminal or the network device, or a logical module or software capable of implementing all or part of the functions of the first communication device. This application does not make any limitations in this regard.

[0007] The method includes: determining an AI model, where the AI model includes multiple levels of sub-models, and each level of sub-model in the multiple levels of sub-models is applicable to at least one object; obtaining an identifier of a target object; based on the identifier of the target object, determining a target sub-model at a level corresponding to the target object; and switching the sub-model at the level corresponding to the target object in the multiple levels of sub-models to the target sub-model.

[0008] In this application, the AI model has a hierarchical structure, including multiple levels of sub-models, and each level of sub-model has at least one object applicable to it, and the object can be a network coverage area or a task.

[0009] The objects applicable to the multi-level sub-models are nested level by level. Or rather, at least one object applicable to the upper-level sub-model includes at least one object applicable to the lower-level sub-model. For example, in the hierarchical structure of the AI model, there are level 1, level 2, and level 3. Among them, level 1 is the upper level of level 2, and level 2 is the upper level of level 3. At least one object applicable to the sub-model of level 1 includes at least one object applicable to the sub-model of level 2, and at least one object applicable to the sub-model of level 2 includes at least one object applicable to the sub-model of level 3.

[0010] Taking the above three levels as an example, one sub-model of level 1 can correspond to one or more sub-models of level 2, and one sub-model of level 2 can correspond to one or more sub-models of level 3. One sub-model of level 1, one sub-model of level 2, and one sub-model of level 3 can be cascaded to form a complete AI model.

[0011] Based on the technical solution of this application, when switching the object, the first communication device can simply switch the sub-model of the level corresponding to the target object in the multi-level sub-models to the target sub-model. The target sub-model is the sub-model applicable to the target object, and if the sub-models of other levels are still applicable to the target object, there is no need to switch. In this way, there is no need to switch the entire AI model, thereby avoiding downloading the complete AI model every time the network coverage area or task is switched, which is beneficial to reducing signaling overhead.

[0012] In combination with the first aspect, in some implementation manners of the first aspect, before determining the AI model, the method further includes: receiving a first message, where the first message indicates the parameters for constructing the AI model, the hierarchical structure of the AI model, and at least one object applicable to each level of the sub-model, and the multi-level sub-models are determined from the AI model based on the hierarchical structure of the AI model.

[0013] In combination with the first aspect, in some implementation manners of the first aspect, the hierarchical structure of the AI model indicates the starting neural network layer and the ending neural network layer of each level of the sub-model in the AI model.

[0014] In combination with the first aspect, in some implementation manners of the first aspect, determining the target sub-model of the level corresponding to the target object based on the identifier of the target object includes: determining whether at least one object applicable to the sub-model of the level corresponding to the target object in the multi-level sub-models includes the target object based on the identifier of the target object; in the case where at least one object applicable to the sub-model of the level corresponding to the target object in the multi-level sub-models does not include the target object, obtaining the parameters for constructing the target sub-model; and constructing the target sub-model based on the parameters for constructing the target sub-model.

[0015] In combination with the first aspect, in some implementations of the first aspect, the parameters for constructing the target sub-model are carried by the following messages: Radio Resource Control (RRC) message, Medium Access Control (MAC) control element (CE), Downlink Control Information (DCI), or Uplink Control Information (UCI).

[0016] In combination with the first aspect, in some implementations of the first aspect, the identifier of the target object is carried in the handover message, and this handover message is used to indicate the handover to the target object.

[0017] In this application, by reusing the handover message in the existing process and combining the binding relationship between the sub-model and the identifier of the target object, the target sub-model applicable to the target object can be determined, and there is no need to additionally send the identifier of the target sub-model, reducing signaling overhead.

[0018] In combination with the first aspect, in some implementations of the first aspect, the multi-level sub-model includes a multi-level sub-model obtained by dividing the AI model based on network coverage areas of multiple different granularities.

[0019] In combination with the first aspect, in some implementations of the first aspect, the object is a network coverage area, and the network coverage areas of multiple different granularities are: the network coverage area of a cell group, the network coverage area of a cell, and the network coverage area of a beam. The multi-level sub-model includes: a first-level sub-model, a second-level sub-model, and a third-level sub-model. The network coverage area applicable to the first-level sub-model is the network coverage area of the cell group, the network coverage area applicable to the second-level sub-model is the network coverage area of at least one cell in the cell group, and the network coverage area applicable to the third-level sub-model is the network coverage area of at least one beam within the at least one cell.

[0020] In combination with the first aspect, in some implementations of the first aspect, the method further includes: storing the first-level sub-model and / or the second-level sub-model. In this way, when switching between different network coverage areas applicable to the first sub-model or the second sub-model, there is no need to receive the parameters for constructing the first sub-model and / or the second sub-model, which is beneficial to reducing signaling overhead.

[0021] In combination with the first aspect, in some implementations of the first aspect, the identifier of the target object includes a cell group identifier, a cell identifier, and a beam identifier.

[0022] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: training / evaluating the sub-model of the level corresponding to the first network coverage area in the multi-level sub-model based on the data collected in the first network coverage area. In this way, it is beneficial to improve the accuracy of training / evaluating the sub-model.

[0023] In combination with the first aspect, in certain implementations of the first aspect, before training / evaluating the sub-model of the level corresponding to the first network coverage area in the multi-level sub-model based on the data collected in the first network coverage area, the method further includes: marking the data collected in the first network coverage area with the identifier of the first network coverage area.

[0024] In combination with the first aspect, in certain implementations of the first aspect, the multi-level sub-model includes a multi-level sub-model obtained by dividing the AI model based on multiple data processing functions, and the multiple data processing functions are the functions provided by the AI model based on the input data.

[0025] In this application, the AI model can provide multiple data processing functions based on the same type of input data. For multiple different tasks in the same task group, when implementing the multiple different tasks, the input data of the AI model is the same type of input data.

[0026] For example, Task 1 and Task 2 belong to the same task group A1. For all tasks in task group A1, that is, Task 1 and Task 2, the input data of the AI model is CSI.

[0027] In combination with the first aspect, in certain implementations of the first aspect, the object is a task, and the multiple data processing functions are: a feature extraction function related to the task group corresponding to the input data, a feature extraction function related to at least one task in the task group, and an output function related to one task in the at least one task. The multi-level sub-model includes: a first-level sub-model, a second-level sub-model, and a third-level sub-model. The first-level sub-model is applicable to the task group, the second-level sub-model is applicable to the at least one task, and the third-level sub-model is applicable to one task in the at least one task.

[0028] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: storing the first-level sub-model and / or the second-level sub-model. In this way, when switching between different tasks applicable to the first-level sub-model or the second-level sub-model, there is no need to receive the parameters for constructing the first-level sub-model and / or the second-level sub-model again, which is beneficial to reducing signaling overhead.

[0029] In combination with the first aspect, in certain implementations of the first aspect, the identifier of the target object includes the identifier of the task group to which the target object belongs.

[0030] In a second aspect, a communication device is provided, including: means for performing the method in any of the possible implementations in the first aspect above. Specifically, the device includes a module for performing the method in any of the possible implementations in the first aspect above.

[0031] In one design, the device may include modules corresponding one by one to the methods / operations / steps / actions described in the first aspect above. The module may be a hardware circuit, software, or a combination of hardware circuit and software.

[0032] In another design, the device is a communication chip, and the communication chip may include an input circuit or interface for sending information or data, and an output circuit or interface for receiving information or data.

[0033] In another design, the device is a terminal or a network device, and the terminal or network device may include a transmitter for sending information or data and a receiver for receiving information or data.

[0034] In another design, the device is used to perform the method in any of the possible implementations in the first aspect above, and the device may be configured in a terminal or a network device.

[0035] In a third aspect, a communication device is provided, including a processor, and the processor is used to call and run a computer program from a memory, so that the device performs the method in any of the possible implementations in the first aspect above.

[0036] Optionally, the device further includes a memory, and the memory can be used to store instructions and data. The memory is coupled to the processor, and when the processor executes the instructions stored in the memory, the methods described in the above aspects can be implemented.

[0037] Optionally, the device further includes: a transmitter (transmitting device) and a receiver (receiving device). The transmitter and the receiver can be separately provided or integrated together, and are called a transceiver.

[0038] In a fourth aspect, another communication device is provided, including a processor, and the processor is used to execute a computer program or instruction in a memory to implement the method in any of the possible implementations in the first aspect above.

[0039] In a fifth aspect, a computer program product is provided, and the computer program product includes: a computer program (which can also be called code, or instruction), and when the computer program is run, it causes a computer to perform the method in any of the possible implementations in the first aspect above.

[0040] In a sixth aspect, a computer-readable storage medium is provided for storing a computer program or instructions. When the computer program or instructions are run on a computer, the method in any of the possible implementation manners in the first aspect above is executed.

[0041] In a seventh aspect, the present application provides a chip system. The chip system includes at least one processor for supporting the implementation of functions involved in any of the possible implementation manners in any of the above aspects. For example, receiving or processing data involved in the above method, etc.

[0042] In a possible design, the chip system further includes a memory for storing program instructions and data. The memory is located inside or outside the processor.

[0043] Optionally, the chip system may be composed of chips or may include chips and other discrete devices. Description of the Drawings

[0044] Figure 1 is a schematic diagram of a neuron structure;

[0045] Figure 2 is a schematic diagram of a neural network structure;

[0046] Figure 3 is a schematic diagram of a communication system provided by an embodiment of the present application;

[0047] Figure 4 is a schematic diagram of model downloading provided by an embodiment of the present application;

[0048] Figure 5 is a schematic diagram of model switching provided by an embodiment of the present application;

[0049] Figure 6 is a schematic flowchart of a model switching method provided by an embodiment of the present application;

[0050] Figure 7 is a schematic diagram of the hierarchical structure of an AI model provided by an embodiment of the present application;

[0051] Figure 8 is a schematic flowchart of another model switching method provided by an embodiment of the present application;

[0052] Figure 9 is a schematic diagram of another model switching provided by an embodiment of the present application;

[0053] Figure 10 is a schematic diagram of the structure of a MAC CE provided by an embodiment of the present application;

[0054] Figure 11It is a schematic diagram of a hierarchical structure of data provided by an embodiment of the present application;

[0055] Figure 12 It is a schematic diagram of an identifier of data provided by an embodiment of the present application;

[0056] Figures 13 to 16 It is a schematic block diagram of a communication device provided by an embodiment of the present application. Detailed implementation manners

[0057] Next, the technical solutions in the present application will be described with reference to the accompanying drawings.

[0058] Before introducing the model switching method and related devices provided by the embodiments of the present application, the following points are explained first.

[0059] First, in the embodiments shown below, each term and English abbreviation, such as AI model, multi-level sub-model, etc., are all exemplary examples given for convenience of description, and should not constitute any limitation to the present application. The present application does not exclude the possibility of defining other terms that can achieve the same or similar functions in existing or future protocols.

[0060] Second, in the embodiments shown below, the first, second, and various numerical numbers are only for distinction for convenience of description, and are not used to limit the scope of the embodiments of the present application.

[0061] Third, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after. "At least one (item)" or its similar expression refers to any combination of these items, including any combination of single item (item) or plural items (items). For example, at least one (item) of a, b, and c can represent: a, or b, or c, or a and b, or a and c, or b and c, or a, b, and c, where a, b, and c can be single or multiple.

[0062] Fourth, the "transmission" and "reception" in this application represent the direction of signal transmission. For example, "sending a model request message to a base station" can be understood as the destination of the model request message being the base station, which can include direct transmission through the air interface, or indirect transmission through the air interface by other units or modules. "Receiving the identifier of a target object from a terminal" can be understood as the source of the identifier of the target object being the terminal, which can include direct reception from the terminal through the air interface, or indirect reception from the terminal through the air interface by other units or modules. "Transmission" can also be understood as the "output" of a chip interface, and "reception" can also be understood as the "input" of a chip interface.

[0063] In other words, transmission and reception can be carried out between devices, for example, between a terminal and a base station; or can be carried out within a device, for example, transmission or reception between components, modules, chips, software modules or hardware modules within a device through a bus, trace or interface.

[0064] The following introduces the related technologies and concepts involved in this application.

[0065] Artificial intelligence can endow machines with human intelligence. For example, it can enable machines to apply computer software and hardware to simulate certain intelligent behaviors of humans. To achieve artificial intelligence, machine learning methods can be adopted. In machine learning methods, a machine learns (or trains) a model using training data. The model represents the mapping from input to output. The learned model can be used for inference (or prediction), that is, the output corresponding to a given input can be predicted using the model. Among them, the output can also be called an inference result (or prediction result).

[0066] Machine learning can include supervised learning, unsupervised learning, and reinforcement learning. Among them, unsupervised learning can also be called non-supervised learning.

[0067] A neural network (NN) is a specific model in machine learning technology. According to the universal approximation theorem, a neural network can theoretically approximate any continuous function, enabling the neural network to have the ability to learn any mapping. Traditional communication systems need to rely on rich expert knowledge to design communication modules, while a deep learning communication system based on a neural network can automatically discover implicit pattern structures from a large dataset, establish a mapping relationship between data, and obtain performance superior to traditional modeling methods.

[0068] The idea of a neural network comes from the neuron structure of brain tissue. Figure 1 is a schematic diagram of a neuron structure. Each neuron performs a weighted summation operation on its input value and outputs the operation result through an activation function. The activation functions of different neurons in a neural network can be the same or different.

[0069] A neural network generally includes multiple layers, and each layer may include one or more neurons. By increasing the depth and / or width of the neural network, the expressive ability of the neural network can be improved, providing a more powerful information extraction and abstract modeling ability for complex systems. Among them, the depth of the neural network can refer to the number of layers included in the neural network, and the number of neurons included in each layer can be referred to as the width of that layer.

[0070] Figure 2 is a schematic diagram of the structure of a neural network, Figure 2 The neural network shown includes an input layer, a hidden layer, and an output layer. The input layer of the neural network processes the received input information through neurons and passes the processing result to the middle hidden layer. The hidden layer calculates the received processing result to obtain a calculation result, and the hidden layer passes the calculation result to the output layer or the next adjacent hidden layer. Finally, the output layer obtains the output result of the neural network. Among them, a neural network may include one hidden layer or multiple sequentially connected hidden layers, without limitation.

[0071] The neural network is, for example, a deep neural network (DNN). According to the construction method of the network, DNN can include a feedforward neural network (FNN), a convolutional neural network (CNN), and a recurrent neural network (RNN).

[0072] In the above model training process of machine learning, a loss function can be defined. The loss function describes the gap or difference between the output value of the model and the ideal target value. The loss function can be embodied in various forms, and there is no limitation on the specific form of the loss function. The model training process can be regarded as the following process: by adjusting some or all of the parameters of the model, the value of the loss function is made less than the threshold value or meets the target requirements.

[0073] The model can also be called an AI model, a rule, or other names, etc. The AI model can be considered as a specific method for implementing AI functions. The AI model represents the mapping relationship or function between the input and output of the model. AI functions can include one or more of the following: data collection, model training (or model learning), model information release, model inference (or also called model reasoning, reasoning, or prediction, etc.), model monitoring or model verification, or release of inference results, etc. AI functions can also be called AI (related) operations or AI-related functions.

[0074] Figure 3It is a schematic diagram of a communication system 1000 provided by an embodiment of the present application. As Figure 3 shown, the communication system 1000 includes a radio access network (RAN) 100 and a core network (CN) 200. The RAN 100 includes at least one RAN node (such as Figure 1 110a and 110b in Figure 1 , collectively referred to as 110) and at least one terminal (such as Figure 3 120a - 120j in

[0075] , collectively referred to as 120). Optionally, the communication system 1000 further includes the Internet 300. It should be understood that Figure 1 is a schematic diagram of a possible, non - restrictive communication system, and this communication system may further include more or fewer devices, which are not limited in this application.

[0076] The RAN 100 may be a cellular system related to the 3rd generation partnership project (3GPP), for example, the 4th generation (4G) mobile communication system, the 5th generation (5G) mobile communication system, or an evolved system for the future, such as the 6th generation (6G). The RAN 100 may also be an open RAN (O - RAN or ORAN), a cloud radio access network (CRAN). The RAN 100 may also be a communication system integrating two or more of the above systems.

[0077] The RAN node 110, sometimes also referred to as an access network device, a RAN entity, or an access node, etc., constitutes a part of the communication system to help the terminal achieve wireless access. The multiple RAN nodes 110 in the communication system 1000 may be of the same type or different types. In some scenarios, the roles of the RAN node 110 and the terminal 120 are relative. For example, Figure 3The intermediate network element 120i can be a helicopter or a drone, which can be configured as a mobile base station. For the terminals 120j accessing the RAN 100 through the network element 120i, the network element 120i is a base station; but for the base station 110a, the network element 120i is a terminal. The RAN nodes 110 and the terminals 120 are sometimes both referred to as communication devices, such as Figure 3 The intermediate network elements 110a and 110b in the figure can be understood as communication devices with base station functions, and the network elements 120a - 120j can be understood as communication devices with terminal functions.

[0078] In a possible scenario, the RAN node can be a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a next generation NodeB (gNB), a next generation base station in a 6G mobile communication system, a base station in a future mobile communication system, etc. The RAN node can be a macro base station (such as Figure 1 110a in the figure), a micro base station or an indoor station (such as Figure 1 110b in the figure), a relay node or a donor node, or a radio controller in a CRAN scenario. Optionally, the RAN node can also be a server, a wearable device, a vehicle or in - vehicle equipment, etc. For example, the access network device in vehicle - to - everything (V2X) technology can be a road side unit (RSU).

[0079] In another possible scenario, multiple RAN nodes cooperate to assist the terminal in achieving wireless access, and different RAN nodes respectively implement some functions of the base station. For example, the RAN node can be a central unit (CU), a distributed unit (DU), a CU - control plane (CP), a CU - user plane (UP), or a radio unit (RU), etc. The CU and the DU can be set separately, or can also be included in the same network element, such as a baseband unit (BBU). The RU can be included in a radio frequency device or a radio frequency unit, such as included in a remote radio unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH).

[0080] In different systems, the CU (or CU-CP and CU-UP), DU, or RU may also have different names, but those skilled in the art can understand their meanings. For example, in the ORAN system, the CU may also be referred to as O-CU (Open CU), the DU may also be referred to as O-DU, the CU-CP may also be referred to as O-CU-CP, the CU-UP may also be referred to as O-CU-UP, and the RU may also be referred to as O-RU. For ease of description, in this application, the CU, CU-CP, CU-UP, DU, and RU are used as examples for description. Any unit among the CU (or CU-CP, CU-UP), DU, and RU in this application may be implemented through a software module, a hardware module, or a combination of a software module and a hardware module.

[0081] The terminal may also be referred to as a terminal device, user equipment (UE), mobile station, mobile terminal, etc. The terminal can be widely applied in various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communication, machine-type communication (MTC), Internet of Things (IoT), virtual reality, augmented reality, industrial control, autonomous driving, remote medical treatment, smart grid, smart furniture, smart office, smart wearables, smart transportation, smart city, etc. The terminal can be a mobile phone, a tablet computer, a computer with wireless transceiver function, a wearable device, a vehicle, a drone, a helicopter, an airplane, a ship, a robot, a robotic arm, a smart home device, etc. The embodiments of this application do not limit the device form of the terminal.

[0082] In the communication system provided in this application (such as Figure 3 the communication system 1000 shown), an AI network element may be introduced to implement some or all of the AI-related operations. The AI network element may also be referred to as an AI node, AI device, AI entity, AI module, AI model, or AI unit, etc. The AI network element may be built into the network element of the communication system. For example, the AI network element may be an AI module built into an access network device, a core network device, a cloud server, or a network management (operation, administration and maintenance, OAM) to implement AI-related functions. The OAM may be the network management of the core network device and / or the network management of the access network device. Alternatively, the AI network element may also be an independently provided network element in the communication system. Or, the terminal or the chip built into the terminal may also include an AI model for implementing AI-related functions. A processing module based on the AI model. For ease of description, this application uses the AI model as an example for description.

[0083] In a communication system, a processing module based on an AI model can, through data-driven model training, optimize modules such as channel coding, modulation, and waveforms in the physical layer, as well as functions such as upper-layer beam management, CSI compression, and positioning according to scenarios, thereby enabling better transmitted signal design and receiving performance. Different AI models may correspond to different network coverage areas or tasks (for example, positioning tasks, beam prediction tasks).

[0084] A network device, a terminal, or other entities can train an AI model for a specific network coverage area and a specific task, and the network device stores the AI model. As Figure 4 shown, UE 1 can download a first AI model that is trained and applicable to the current network coverage area or task from Base Station 1. When the terminal moves and causes a handover of the network coverage area, or when the task changes, the terminal needs to switch the AI model, which can be referred to Figure 5 .

[0085] As Figure 5 shown, UE 1 is within Network Coverage Area 1 of Base Station 1, and UE 1 downloads a first AI model applicable to Network Coverage Area 1 from Base Station 1. When UE 1 switches from the network coverage area of Base Station 1 to Network Coverage Area 2 of Base Station 2, and the first AI model is no longer applicable to Network Coverage Area 2, after UE 1 accesses Base Station 2, Base Station 2 indicates the identifier of the second AI model to UE 1, indicating that the model applicable to Network Coverage Area 2 for UE 1 is the second AI model. Subsequently, UE 1 downloads the second AI model applicable to Network Coverage Area 2 from Base Station 2.

[0086] Due to the limited storage capacity of the terminal, it may not be possible to pre-store all AI models. Therefore, in each handover scenario, the terminal may need to download the AI model from the network device side. However, downloading a complete AI model from the network device side will incur a large signaling overhead.

[0087] In view of this, an embodiment of the present application provides a model switching method. In this method, the AI model is divided into multiple levels of sub-models, and each level of sub-model has its applicable network coverage area or task. In the scenario where the network coverage area or task changes, the communication device only needs to switch the sub-model of the level corresponding to the switched network coverage area or task among the multiple levels of sub-models, which can avoid downloading a complete AI model during switching, thereby helping to reduce signaling overhead.

[0088] The following will specifically introduce the model switching method provided by the embodiment of the present application in combination with Figures 6 to 12 .

[0089] Figure 6It is a schematic flowchart of a model switching method 600 provided by an embodiment of the present application. The embodiment of the present application relates to model switching in a switching scenario, and the switching scenario may include: switching the network coverage area, or switching tasks. The switching of the network coverage area or the switching of tasks may be initiated by the terminal or by the network device.

[0090] The method of the embodiment of the present application may be executed by a first communication device, and the first communication device is a terminal or a network device. When the first communication device is a terminal, the second communication device is a network device. When the first communication device is a network device, the second communication device is a terminal.

[0091] The network device may be, for example, Figure 3 the RAN node 100 in, having possible forms as described for the RAN node 100, for example, a base station in 4G or 5G, or a next-generation base station in a 6G system, or a base station in a future mobile communication system. Or, the RAN node is a CU (CU-CP, CU-UP), DU, RU, near-real-time radio network intelligent controller (RAN intelligent controller, RIC) or non-real-time RIC, and the present application does not limit this.

[0092] The method 600 includes S601 to S604, and the specific steps are as follows:

[0093] S601, determine an AI model, the AI model includes multiple levels of sub-models, and each level of sub-model in the multiple levels of sub-models is applicable to at least one object, and the object is a network coverage area or a task.

[0094] In this step, when the first communication device needs to optimize a certain radio function (for example, channel coding, modulation or waveform design) in the current network coverage area, or needs to execute a certain task, the AI model can be determined. The AI model has multiple levels of sub-models, and each level of sub-model is applicable to at least one object, and the at least one object includes the current network coverage area of the first communication device or the current task to be executed.

[0095] For ease of description, hereinafter, the current network coverage area of the first communication device or the current task to be executed will be referred to as the initial object, and the sub-model in the multiple levels of sub-models that is applicable to the initial object will be referred to as the initial sub-model. Among them, the current network coverage area of the first communication device may also be described as the network coverage area before the first communication device switches, and the current task to be executed by the first communication device may also be described as the task to be executed before the first communication device switches.

[0096] In this step, the AI model is an AI model applicable to the initial object, that is, at least one object applicable to each level of the multi-level sub-models of the AI model includes the initial object.

[0097] Optionally, before S601, the first communication device receives a first message from the second communication device. The first message indicates the parameters for constructing the AI model, the hierarchical structure of the AI model, and at least one object applicable to each level of sub-model. The multi-level sub-models are determined from the AI model based on the hierarchical structure of the AI model.

[0098] Optionally, the first message is an RRC message.

[0099] S601 may include: The first communication device determines the AI model based on the first message. Moreover, the first communication device may determine the multi-level sub-models of the AI model and at least one object applicable to each level of sub-model according to the first message.

[0100] Based on the indication of the first message, the AI model can be divided into multiple levels, and each level has its corresponding sub-model. Or rather, the AI model can be divided into multiple modules, and each module has its corresponding sub-model. The objects applicable to the sub-models of multiple levels are nested with each other. For reference, please refer to the description in the following text for Figure 7 the

[0101] Figure 7 is a schematic diagram of the hierarchical structure of an AI model provided by an embodiment of this application. Exemplarily, the AI model is divided into three levels, including Level 1, Level 2, and Level 3. The sub-model of Level 1 includes Sub-model 1, the sub-models of Level 2 include Sub-model 2 and Sub-model 3, and the sub-models of Level 3 include Sub-model 4, Sub-model 5, Sub-model 6, and Sub-model 7.

[0102] Among them, at least one object applicable to the sub-model of Level 1 includes at least one object applicable to the sub-model of Level 2, and at least one object applicable to the sub-model of Level 2 includes at least one object applicable to the sub-model of Level 3. Specifically, at least one object applicable to Sub-model 1 includes at least one object applicable to Sub-model 2 and at least one object applicable to Sub-model 3. At least one object applicable to Sub-model 2 includes at least one object applicable to Sub-model 4 and at least one object applicable to Sub-model 5. At least one object applicable to Sub-model 3 includes at least one object applicable to Sub-model 6 and at least one object applicable to Sub-model 7.

[0103] For sub-models at the same level, different sub-models may be applicable to different objects. For example, at least one object applicable to sub-model 2 is different from at least one object applicable to sub-model 3, and at least one object applicable to sub-model 4 is different from at least one object applicable to sub-model 5.

[0104] It should be noted that cascading sub-models at multiple levels can form a complete AI model.

[0105] For example, cascading sub-model 1, sub-model 2, and sub-model 4 forms a complete AI model.

[0106] For another example, cascading sub-model 1, sub-model 2, and sub-model 5 forms a complete AI model.

[0107] For another example, cascading sub-model 1, sub-model 2, and sub-model 5 forms a complete AI model.

[0108] For another example, cascading sub-model 1, sub-model 3, and sub-model 6 forms a complete AI model.

[0109] For another example, cascading sub-model 1, sub-model 3, and sub-model 7 forms a complete AI model.

[0110] It should be noted that the AI model determined in this step is, for example, the AI model formed by cascading sub-model 1, sub-model 2, and sub-model 4 as described above. In other words, the multi-level sub-models in this step include sub-model 1, sub-model 2, and sub-model 4.

[0111] S602, obtain the identifier of the target object.

[0112] In the case where the first communication device needs to switch from the initial object to the target object, the first communication device obtains the identifier of the target object, and then determines the target sub-model at the corresponding level of the target object. For example, due to terminal movement resulting in cell handover of the terminal, the terminal needs to access the target cell. In this case, the terminal can obtain the identifier of the target cell.

[0113] For ease of description, in the following text, the level corresponding to the target object among multiple levels is called the target level. In the above multi-level sub-models, the sub-model at the target level applicable to the initial object can be called the initial sub-model at the target level. Among them, the target level can be one or more of the multiple levels.

[0114] The first communication device obtaining the identifier of the target object includes the following two cases:

[0115] Case 1, the first communication device determines the target object and obtains the identifier of the target object.

[0116] Case 2, the first communication device receives the identifier of the target object from the second communication device. In this case, the second communication device determines the target object and sends the identifier of the target object to the first communication device.

[0117] S603. Based on the identifier of the target object, determine the target sub-model of the level corresponding to the target object. The target sub-model is applicable to the target object.

[0118] After the first communication device obtains the identifier of the target object, since the first communication device knows at least one object applicable to each level of the sub-model, after knowing the identifier of the target object, the first communication device can determine whether at least one object applicable to the sub-model of the target level includes the target object from the correspondence between each level of the sub-model and at least one applicable object.

[0119] In a possible implementation, S603 may include: based on the identifier of the target object, determine that at least one object applicable to the sub-model of the target level does not include the target object; obtain the parameters for constructing the target sub-model; based on the parameters for constructing the target sub-model, construct the target sub-model.

[0120] Combined with the above example for Figure 7 The multi-level sub-models of the AI model applicable to the initial object include sub-model 1, sub-model 2, and sub-model 4. If switching from the initial object to the target object, and the level corresponding to the target object is level 3, and the first communication device determines that at least one object applicable to sub-model 4 does not include the target object, then the first communication device needs to obtain the parameters for constructing the target sub-model to construct the target sub-model. The target sub-model is, for example, sub-model 5 in level 3.

[0121] It should be noted that the target level can be one or more. When the target level is multiple, each target level will correspond to a target sub-model. Taking Figure 7 as an example, when the target level includes level 1, the target sub-model of level 1 (such as the cell group layer or the common feature extraction layer in the following text) can be called target sub-model 1. When the target level includes level 2, the target sub-model of level 2 (such as the cell layer or the task feature extraction layer in the following text) can be called target sub-model 2. When the target level includes level 3, the target sub-model of level 3 (such as the beam layer or the task output layer in the following text) can be called target sub-model 3.

[0122] For the specific process of determining the target level, refer to the description in the following text, which will not be elaborated here for the time being.

[0123] Optionally, the first communication device obtains the parameters for constructing the target sub-model, including: the first communication device receives the parameters for constructing the target sub-model from the second communication device.

[0124] Optionally, when the first communication device is a terminal and the second communication device is a network device, the parameters for constructing the target sub-model can be carried by an RRC message, a MAC CE, or DCI.

[0125] Optionally, when the first communication device is a network device and the second communication device is a terminal, the parameters for constructing the target sub-model can be carried by UCI.

[0126] The further description of the first communication device receiving the parameters for constructing the target sub-model from the second communication device is as follows:

[0127] Combined with Case 1 in S602, before the first communication device receives the parameters for constructing the target sub-model from the second communication device, the first communication device can send the identifier of the target object to the second communication device. After receiving the identifier of the target object, the second communication device determines the target sub-model corresponding to the target object based on the stored correspondence information between the sub-model and the object. Furthermore, the second communication device can send the parameters for constructing the target sub-model to the first communication device. Correspondingly, the first communication device receives the parameters for constructing the target sub-model.

[0128] Combined with Case 2 in S602, after the second communication device determines the target object, it determines the target sub-model corresponding to the target object from the stored correspondence information between the sub-model and the object. Furthermore, the second communication device sends the parameters for constructing the target sub-model to the first communication device. Correspondingly, the first communication device receives the parameters for constructing the target sub-model from the second communication device.

[0129] Optionally, the second communication device sending the parameters for constructing the target sub-model to the first communication device includes: the second communication device sending the parameters for constructing the target sub-model to the first communication device based on the first request message. In this implementation, after the first communication device receives the identifier of the target object from the second communication device, based on the identifier of the target object, it determines that at least one object applicable to the sub-model at the target level does not include the target object. Furthermore, the first communication device sends the first request message to the second communication device, and the first request message is used to request the sub-model applicable to the target object.

[0130] In another possible implementation, S603 may include: based on the identifier of the target object, determining that at least one object applicable to the sub-model at the target level includes the target object; and determining the initial sub-model at the target level as the target sub-model at the target level. In this implementation, the target sub-model at the target level determined by the first communication device is the initial sub-model at the target level.

[0131] Combined with the above for Figure 7For an example applicable to a multi-level sub-model of an AI model for an initial object, the multi-level sub-model includes Sub-model 1, Sub-model 2, and Sub-model 4. If switching from the initial object to a target object, and the level corresponding to the target object is Level 3, and the first communication device determines that at least one object applicable to Sub-model 4 at Level 3 includes the target object, then the first communication device determines Sub-model 4 as the target sub-model.

[0132] S604, switch the sub-model at the level corresponding to the target object in the multi-level sub-model to the target sub-model.

[0133] In this step, the sub-model at the target level is the initial sub-model at the target level, that is, the sub-model applicable to the initial object in the multi-level sub-model. The first communication device switches the initial sub-model applicable to the initial object at the target level to the target sub-model applicable to the target object.

[0134] As can be seen from the above description, the objects applicable to the sub-models at multiple levels are nested with each other. Therefore, when the first communication device switches to the target object, there may be a situation where the initial sub-models of some levels among multiple levels are not applicable to the target object, but the initial sub-models of other levels are still applicable to the target object.

[0135] Illustrate with an example. Referring to the above example for Figure 7 For an example applicable to a multi-level sub-model of an AI model for an initial object, the multi-level sub-model includes Sub-model 1, Sub-model 2, and Sub-model 4. The objects applicable to Sub-model 1 at Level 1 include Object 1, Object 2, Object 3, and Object 4. The objects applicable to Sub-model 2 at Level 2 include Object 1 and Object 2. The objects applicable to Sub-model 4 at Level 3 include Object 1. The target object is Object 2, and the target level is Level 3.

[0136] In this example, the objects applicable to Sub-model 4 at Level 3 do not include Object 2, but the objects applicable to Sub-model 1 at Level 1 include Object 2, and the objects applicable to Sub-model 2 at Level 2 also include Object 2. Therefore, in the scenario of switching objects, the first communication device only needs to switch the sub-model at Level 3 to the sub-model applicable to Object 2, and there is no need to obtain the target sub-models at Level 1 and Level 2 anymore.

[0137] In the embodiment of this application, the first communication device switches the sub-model at the target level in the multi-level sub-model to the target sub-model. The initial sub-models of other levels among multiple levels are still applicable to the target object. Therefore, there is no need to obtain the target sub-models of other levels anymore, which is beneficial to avoiding downloading the complete AI model and thus reducing signaling overhead.

[0138] The above object can be a network coverage area or a task. First, the model switching process when the object is a network coverage area will be described in combination with Figures 8 to 12 introduce.

[0139] Optionally, when the above object is a network coverage area, the multi-level sub-model includes a multi-level sub-model obtained by dividing the AI model based on network coverage areas with multiple different granularities.

[0140] In a possible implementation, the network coverage areas with multiple different granularities include the network coverage area of a cell group, the network coverage area of a cell, and the network coverage area of a beam. In this way, the AI model is divided into three levels, namely the cell group level, the cell level, and the beam level.

[0141] In another possible implementation, the network coverage areas with multiple different granularities include the network coverage area of a cell and the network coverage area of a beam. In this way, the AI model is divided into two levels, namely the cell level and the beam level.

[0142] In another possible implementation, the network coverage areas with multiple different granularities include the network coverage area of a cell group, the network coverage area of a cell, the network coverage area of a sector, and the network coverage area of a beam. In this way, the AI model is divided into four levels, namely the cell group level, the cell level, the sector level, and the beam level.

[0143] The following takes the network coverage areas with multiple different granularities including the network coverage area of a cell group, the network coverage area of a cell, and the network coverage area of a beam as an example for introduction.

[0144] The above multi-level sub-model includes a first-level sub-model (such as Figure 7 sub-model 1 in Figure 7 ), a second-level sub-model (such as Figure 7 sub-model 2 in

[0145] Figure 8 ), and a third-level sub-model (such as

[0146] Figure 7 sub-model 4 in

[0145] Figure 8 ). Among them, the first-level sub-model is the sub-model at the cell group level, and the network coverage area applicable to the first-level sub-model is the network coverage area of the cell group; the second-level sub-model is the sub-model at the cell level, and the network coverage area applicable to the second-level sub-model is the network coverage area of at least one cell in the cell group; the third-level sub-model is the sub-model at the beam level, and the network coverage area applicable to the third-level sub-model is the network coverage area of at least one beam in the at least one cell.

[0146] Method 800 includes S801 to S806, and the specific steps are as follows:

[0147] S801, the terminal sends a model request message to the base station, and this model request message is used to request an AI model. Correspondingly, the base station receives this model request.

[0148] Exemplarily, after the terminal accesses the base station, the terminal is within the network coverage area of a beam (denoted as beam C1) of a cell (denoted as cell B1) of the base station, and cell B1 is a cell within a cell group (denoted as cell group A1). Based on this, the AI model sent by the base station is an AI model applicable to the network coverage area of beam C1 of cell B1 in cell group A1.

[0149] S802, the base station sends a model response message to the terminal, and this model response message indicates the parameters used to construct this AI model, the hierarchical structure of this AI model, and at least one object applicable to each level of sub-model. Correspondingly, the terminal receives this model response message.

[0150] The model response message in this step can correspond to the first message in the above text. The introduction of the hierarchical structure of the AI model can refer to the description of S601 in the above text, and will not be elaborated here.

[0151] Referring to the description of S801, this AI model includes a first-level sub-model applicable to the network coverage area of cell group A1, a second-level sub-model applicable to the network coverage area of cell B1, and a third-level sub-model applicable to the network coverage area of beam C1. Since the network coverage area of cell group A1 includes the network coverage area of cell B1, and the network coverage area of cell B1 includes the network coverage area of beam C1, therefore, the network coverage area applicable to the first-level sub-model includes the network coverage area applicable to the second-level sub-model, and the network coverage area applicable to the second-level sub-model includes the network coverage area applicable to the third-level sub-model.

[0152] Optionally, since the network coverage areas applicable to the first sub-model and the second sub-model are relatively large, therefore, the first communication device can store the first sub-model and / or the second sub-model. In this way, when switching between different network coverage areas applicable to the first sub-model and / or the second sub-model, there is no need to receive the parameters used to construct the first sub-model and / or the second sub-model again, which is conducive to reducing signaling overhead.

[0153] Optionally, the hierarchical structure of this AI model can indicate the identifiers of the starting neural network layer and the ending neural network layer of the first-level sub-model, the second-level sub-model, and the third-level sub-model in this AI model respectively.

[0154] Taking the AI model including a 30-layer neural network as an example, Table 1 shows the correspondence between a multi-level sub-model and the network coverage area. The first-level sub-model includes the 1st to 10th neural networks in the 30-layer neural network and is applicable to the network coverage area of cell group A1. The second-level sub-model includes the 11th to 20th neural networks in the 30-layer neural network and is applicable to the network coverage area of cell group B1. The third-level sub-model includes the 21st to 30th neural networks in the 30-layer neural network and is applicable to the network coverage area of beam C1.

[0155] Table 1

[0156] Layers 1 to 10 Layers 11 to 20 Layers 21 to 30 Sub - group A1 Cell B1 Beam C1

[0157] Different network coverage areas are distinguished by different identifiers. Optionally, the identifiers of the network coverage area include the identifier of the cell group, the identifier of the cell, and the identifier of the beam.

[0158] In an example 1, the identifier of the network coverage area of beam C1 in cell B1 of cell group A1 can be: A1-B1-C1.

[0159] In another example 2, the identifier of the network coverage area of beam C2 in cell B1 of cell group A1 can be: A1-B1-C2.

[0160] In another example 3, the identifier of the network coverage area of beam C3 in cell B2 of cell group A1 can be: A1-B2-C3.

[0161] In another example 4, the identifier of the network coverage area of beam C4 in cell B3 of cell group A2 can be: A2-B3-C4.

[0162] Optionally, the level corresponding to the target object can be determined based on the identifier of the target object.

[0163] For example, the identifier of the initial object is A1-B1-C1, and the identifier of the target object is A1-B1-C2. It can be seen that the cell group identifier and the cell identifier remain unchanged, while the beam identifier changes from C1 to C2. Then, the level corresponding to the target object includes the beam level.

[0164] Another example, the identifier of the initial object is A1-B1-C1, and the identifier of the target object is A1-B2-C3. It can be seen that the cell group identifier remains unchanged, while the cell identifier changes from B1 to B2, and the beam identifier changes from C1 to C3. Then, the level corresponding to the target object includes the cell level and the beam level.

[0165] For another example, the identifier of the initial object is A1-B1-C1, and the identifier of the target object is A2-B3-C4. It can be seen that the cell group identifier changes from A1 to A2, the cell identifier changes from B2 to B3, and the beam identifier changes from C1 to C4. Then, the levels corresponding to the target object include the cell group level, the cell level, and the beam level.

[0166] The above representation form of the identifier of the network coverage area is only an example. In addition, other forms can be used to represent the identifier of the network coverage area, and this application does not limit this. For example, the identifier of a cell group is 000, the identifier of a cell within this cell group is 01, and the identifier of a beam within this cell is 0. Then, the identifier of the network coverage area of the beam of the cell within this cell group can be expressed as: 000-01-0.

[0167] The above method of marking the network coverage area can be called the method based on the absolute identifier. In addition, the network coverage area can also be marked by using the method based on the relative identifier.

[0168] For example, the beams of cell B1 in cell group A1 and the beams of cell B2 in cell group A1 use the same identifier, for example, both are beam C, that is, the beam within cell B1 in cell group A1 and the beam within cell B2 in cell group A1 may be the same, but the network coverage areas of the two beams C are different. Therefore, when switching from cell B1 to cell B2, the identifier of the initial object is A1-B1-C, and the identifier of the target object is A1-B2-C. Among them, the beam identifier remains unchanged, but usually cell switching will cause beam switching. Therefore, the levels corresponding to the target object include the cell level and the beam level.

[0169] S803-1, the first case, the terminal sends a handover message to the base station, and this handover message is used to indicate that the terminal is to be handed over to the target network coverage area. Correspondingly, the base station receives this handover message.

[0170] In a possible situation, the terminal needs to be handed over to the target network coverage area due to movement. Therefore, the terminal can send a handover message to the base station, and this handover message carries the identifier of the target network coverage area.

[0171] In an example, the initial network coverage area of the terminal is the network coverage area of beam C1 of cell B1 in cell group A1, and the target network coverage area is the network coverage area of beam C2 of cell B1 in cell group A1. Then, the identifier of the target network coverage area carried in the handover message can be: A1-B1-C2.

[0172] S803-2, the second case, the base station sends a handover message to the terminal, and this handover message is used to indicate that the terminal is to be handed over to the target network coverage area. Correspondingly, the terminal receives this handover message.

[0173] In a possible scenario, the base station determines that the signal quality of the target network coverage area meets the conditions. Therefore, the base station can instruct the terminal to switch to the target network coverage area through a handover message.

[0174] S804. The base station determines whether to send parameters for constructing the target sub-model to the terminal based on the identifier of the target network coverage area.

[0175] When the terminal needs to switch to the target network coverage area, the terminal needs to switch the current AI model to an AI model applicable to the target network coverage area. Based on the above introduction to the hierarchical structure of the AI model, it can be seen that when switching the model, only the sub-model of the target layer needs to be switched to the target sub-model applicable to the target network coverage area. Therefore, after the base station determines the identifier of the target network coverage area, it can determine whether to send parameters for constructing the target sub-model to the terminal based on the stored correspondence information between the sub-model and the network coverage area.

[0176] If the initial sub-model of the target layer in the above multi-level sub-model is also applicable to the target network coverage area, the base station may not send the parameters for constructing the target sub-model to the terminal device.

[0177] If the initial sub-model of the target layer in the above multi-level sub-model is not applicable to the target network coverage area, the base station executes S805.

[0178] S805. The base station sends the parameters for constructing the target sub-model to the terminal. Correspondingly, the terminal receives the parameters for constructing the target sub-model.

[0179] Optionally, the parameters for constructing the target sub-model can be carried by the following messages: RRC message, MAC CE, or DCI.

[0180] Optionally, the base station can indicate the parameters for constructing the AI model through an RRC message. The parameters can include the identifier of the model function, the model structure, the parameters of each layer of the neural network, etc. A possible configuration signaling structure of the AI model in the RRC message is as follows:

[0181]

[0182]

[0183] Among them, "nnAPIIdex" indicates the identification of the model function of the AI model, "Layer index" indicates the identification of a certain layer of neural network, "Layer type" indicates the type of a certain layer of neural network, "Layer parameter" indicates the parameters of a certain layer of neural network, "neuralnetwork weights" indicates the weights of neurons, and "compressionparameters" indicates the compression parameters of the neural network.

[0184] Optionally, the base station may indicate the parameters of the target sub-model for constructing the target level through MAC CE. Figure 10 It is a schematic structural diagram of a MAC CE provided by an embodiment of the present application. In Figure 10 it, "nnID" indicates the identification of the AI model, "nnAPIIdex" indicates the identification of the model function of the AI model, layer identification (LID) indicates a certain layer of neural network in the sub-model of the target level, and LID i indicates the i-th parameter of this layer of neural network, where i ranges from 0 to 7, and W1……W m indicates the weights of the neurons in this layer.

[0185] Optionally, the base station may indicate the parameters of the target sub-model for constructing the target level through DCI. The base station may explicitly indicate the identification of the target level, or the base station implicitly indicates the identification of the target level by means of cyclic redundancy check (CRC) scrambling, etc., or the base station binds and transmits DCI and physical downlink shared channel (PDSCH), indicates the identification of the target level through DCI, and bears the weight value for update through PDSCH.

[0186] Optionally, when the sub-model of a certain level needs to be updated, the base station may indicate a part of the weights of the sub-model of this level through an extended DCI, and this part of the weights is used to update the sub-model of this level.

[0187] S806, the terminal performs model switching.

[0188] Based on the description of S804, if the initial sub-model of the target level in the above multi-level sub-model is not applicable to the target network coverage area, the base station determines to send the parameters for constructing the target sub-model to the terminal device. Correspondingly, the terminal receives the parameters for constructing the target sub-model to construct the target sub-model, and switches the initial sub-model of the target level in the multi-level sub-model to the target sub-model.

[0189] If the initial sub-model of the target level in the above multi-level sub-models is also applicable to the target network coverage area, the sub-model before switching and the sub-model after switching in the target level of the multi-level sub-models are the same.

[0190] In the embodiments of the present application, when the terminal switches the network coverage area, it can switch the sub-model of the target level according to the hierarchical structure of the AI model, which is beneficial to avoiding excessive signaling overhead caused by downloading the complete AI model during switching.

[0191] In addition, when the terminal switches the network coverage area, it indicates model switching according to the handover message used to request the network coverage area handover. Furthermore, the base station can determine the target sub-model applicable to the target network coverage area according to the corresponding relationship information between the network coverage area and the sub-model. In this way, there is no need for the base station to send the model identifier, which is beneficial to reducing signaling overhead.

[0192] Combined with method 800, Figure 9 is another schematic diagram of model switching provided by the embodiments of the present application. As Figure 9 shown, after the terminal initially accesses a cell of the base station, the following several handover scenarios may exist:

[0193] Scenario 1: Beam switching within the same cell. In this scenario, the target level includes the beam layer, and the terminal can switch the sub-model of the beam layer to the target sub-model.

[0194] Referring to Example 1 and Example 2 in S802 above, the initial network coverage area is the network coverage area of Beam C1 in Cell B1 of Cell Group A1. When switching from Beam C1 to Beam C2, the target network coverage area is the network coverage area of Beam C2 in Cell B1 of Cell Group A1. Since Beam C1 and Beam C2 belong to the same Cell B1, only the switching of the sub-model of the beam layer is involved. Then the terminal determines the target sub-model of the beam layer and switches the sub-model of the beam layer to the target sub-model. Among them, at least one object applicable to the target sub-model includes the network coverage area of Beam C2 in Cell B1 of Cell Group A1.

[0195] Scenario 2: Beam switching between different cells. In this scenario, the target level includes the cell layer and the beam layer, and the terminal can switch the sub-model of the cell layer and the sub-model of the beam layer to the target sub-model. It should be understood that the number of target sub-models at this time is multiple, including the target sub-model 2 of the cell layer and the target sub-model 3 of the beam layer.

[0196] Referring to Example 1 and Example 3 in S802 above, the initial network coverage area is the network coverage area of beam C1 of cell B1 in cell group A1. When switching from beam C1 to beam C3, since beam C3 is a beam of cell B2 and belongs to a different cell from beam C1, therefore, switching from beam C1 to beam C3 will simultaneously trigger a handover from cell B1 to cell B2, that is, the target network coverage area is the network coverage area of beam C3 of cell B2 in cell group A1. The terminal determines the target sub-model 2 at the cell layer and the target sub-model 3 at the beam layer, and switches the sub-model at the cell layer to the target sub-model 2 and the sub-model at the beam layer to the target sub-model 3.

[0197] It should be understood that the target sub-model 2 at the cell layer is different from the target sub-model 3 at the beam layer. At least one object applicable to the target sub-model 2 at the cell layer includes the network coverage area of cell B2 in cell group A1, and at least one object applicable to the target sub-model 3 at the beam layer includes the network coverage area of beam C3 of cell B2 in cell group A1.

[0198] Scenario 3: Handover between cells within the same cell group, and usually cell handover will cause beam handover. In this scenario, the target hierarchy includes the cell layer and the beam layer, and the terminal can switch the sub-models at the cell layer and the beam layer to the target sub-models. Similar to the description for Scenario 2, the number of target sub-models is multiple, including the target sub-model 2 at the cell layer and the target sub-model 3 at the beam layer.

[0199] Similar to the example in Scenario 2 above, when switching from cell B1 to cell B2, the corresponding beam also switches from beam C1 of cell B1 to beam C3 of cell B2, and the target network coverage area is the network coverage area of beam C3 of cell B2 in cell group A1. The terminal needs to determine the target sub-model 2 at the cell layer and the target sub-model 3 at the beam layer. Among them, the target sub-model 2 is applicable to the network coverage area of cell B2 in cell group A1, and the target sub-model 3 is applicable to the network coverage area of beam C3 of cell B2 in cell group A1.

[0200] Scenario 4: Handover between different cell groups, which means that it will simultaneously trigger cell group handover, cell handover, and beam handover. In this scenario, the target hierarchy includes the cell group layer, the cell layer, and the beam layer, and the terminal can switch the sub-models at the cell group layer, the cell layer, and the beam layer to the target sub-models.

[0201] Referring to Example 1 and Example 4 in S802 above, when switching from cell B1 to cell B3, since cell B1 belongs to cell group A1, cell B3 belongs to cell group A2, and the beam of cell B1 is beam C1 while the beam of cell B3 is beam C4, accordingly, there will also be a handover from cell group A1 to cell group A2 and a handover from beam C1 to beam C4, that is, the target network coverage area is the network coverage area of beam C4 of cell B3 in cell group A2. The terminal determines the target sub-model 1 at the cell group layer, the target sub-model 2 at the cell layer, and the target sub-model 3 at the beam layer, and switches the sub-model at the cell group layer to the target sub-model 1, switches the sub-model at the cell layer to the target sub-model 2, and switches the target sub-model at the beam layer to the target sub-model 3.

[0202] The cell handover between different cell groups in Scenario 4 can also be understood as a cell group handover. When a cell group handover occurs, it may be necessary to switch the sub-models at the cell group layer, the cell layer, and the beam layer, that is, to switch the AI model applicable to the initial target network coverage area to the AI model applicable to the target network coverage area.

[0203] To train / evaluate the sub-models at different hierarchical levels corresponding to different network coverage areas, it is necessary to bind the data collected within a certain network coverage area to the sub-model at the hierarchical level corresponding to that network coverage area. The purpose of binding is to use the data collected within that network coverage area to train / evaluate the sub-model at the hierarchical level corresponding to that network coverage area.

[0204] Corresponding to the cell group layer, cell layer, and beam layer of the above AI model, the data collected within different cell groups is called cell group data, the data collected within a cell is called in-cell data, and the data collected within a beam is called in-beam data. As Figure 11 shown, the in-cell group data includes in-cell data, and the in-cell data includes in-beam data.

[0205] In terms of the scope of application, the in-beam data can be used to train the complete AI model. In other words, the in-beam data is applicable to training the sub-models at the cell group layer, the cell layer, and the beam layer. The inter-beam data can be used to jointly train the sub-models at the cell layer and the cell group layer, or to evaluate (including monitoring or verification) the performance of multiple sub-models at the beam layer, evaluate the performance of the sub-model at the cell layer, or evaluate the performance of the sub-model at the cell group layer. The in-cell data can be used to train the sub-models at the cell layer and the cell group layer, and the inter-cell data can be used to train the cell group model. In addition, the performance of the sub-model at the cell group layer can also be evaluated by combining the sub-model at the beam layer or the sub-model at the cell layer.

[0206] In a possible implementation, data collected in a network coverage area can be marked with an identifier of the network coverage area, thereby binding the data collected in the network coverage area to a sub-model of the level corresponding to the network coverage area.

[0207] Figure 12 It is a schematic diagram of an identifier of data provided by an embodiment of the present application. It can be seen that the identifier of the data also has a hierarchical structure, including a cell group identifier, a cell identifier, and a beam identifier cascaded to form the identifier of the data.

[0208] For example, the identifier of the data collected in the network coverage area of beam C1 in cell B1 of cell group A1 can be: A1-B1-C1. It can also be understood that the identifier of the network coverage area of beam C1 in cell B1 of cell group A1 is A1-B1-C1, and the data collected in the network coverage area of beam C1 in cell B1 of cell group A1 is marked with A1-B1-C1. In this way, before training, the first communication device can determine the data corresponding to the network coverage area of beam C1 in cell B1 of cell group A1 according to the identifier of the data, that is, determine the data collected in the network coverage area of beam C1 in cell B1 of cell group A1, and then use the data collected in the network coverage area of beam C1 in cell B1 of cell group A1 to train / evaluate the sub-model of the level corresponding to the network coverage area of beam C1 in cell B1 of cell group A1.

[0209] When training a model based on the identifier of the data, the data collected within the beam can be used to train a complete AI model or to evaluate the performance of the sub-model at the beam level.

[0210] In the above method 800, the object is the network coverage area. When the first communication device switches to the target network coverage area, it triggers model switching. When switching the model, the first communication device only needs to switch the sub-model of the target level in the multi-level sub-model to the target sub-model, and the target sub-model is the sub-model applicable to the target network coverage area. Next, the hierarchical structure of the AI model when the object is a task is introduced.

[0211] Optionally, the task can be positioning, environmental object detection, beam prediction, mobile trajectory prediction, etc. Multiple tasks can be grouped according to the task type, and tasks with the same type are grouped into the same task group. For example, environmental object detection and mobile trajectory prediction are both of the perception type and can be grouped into the same task group.

[0212] Different tasks have different task identifiers, and different task groups also have different task group identifiers. When a certain task belongs to a certain task group, when identifying this task, the identifier of the task group to which this task belongs can be added. In other words, the identifier of a task can include the identifier of the task group to which this task belongs and the identifier of this task itself.

[0213] In an example 5, task group A1 includes task 1, task 2, task 3, and task 4. Then the identifier of task 1 is: A1-1; the identifier of task 2 is: A1-2, the identifier of task 3 is: A1-3, and the identifier of task 4 is A1-4.

[0214] In another example 6, task group A2 includes task 5, task 6, and task 7. Then the identifier of task 5 is: A2-5; the identifier of task 6 is: A2-6, and the identifier of task 7 is: A2-7.

[0215] Task group A1 or task group A2 can be further divided into multiple sub-task groups.

[0216] In an example 7, task group A1 is divided into sub-task group B1 and sub-task group B2. Among them, sub-task group B1 includes task 1 and task 2, and sub-task group B2 includes task 3 and task 4. Then the identifier of task 1 can be: A1-B1-1; the identifier of task 2 can be A1-B1-2; the identifier of task 3 can be A1-B2-3; the identifier of task 4 can be A1-B2-4.

[0217] In another example 8, task group A2 is divided into sub-task group B3 and sub-task group B4. Among them, sub-task group B3 includes task 5 and task 6, and sub-task group B4 includes task 7. Then the identifier of task 5 can be: A2-B3-5; the identifier of task 6 can be A2-B3-6; the identifier of task 7 can be: A2-B4-7.

[0218] Optionally, when the above object is a task, the multi-level sub-model includes a multi-level sub-model obtained by dividing the AI model based on multiple data processing functions, and the multiple data processing functions are functions provided by the AI model based on the input data.

[0219] In a possible implementation manner, the multiple data processing functions include: a feature extraction function related to the task group corresponding to the input data (hereinafter may be simply referred to as a common feature extraction function), a feature extraction function related to at least one task in this task group (hereinafter may be simply referred to as a task feature extraction function), and an output function related to one task in this at least one task (hereinafter may be simply referred to as an output function).

[0220] In this implementation manner, in combination Figure 7, the three levels of the AI ​​model are the common feature extraction layer, the task feature extraction layer and the task output layer. Among them, the sub-model of the common feature extraction layer can be called the first-level sub-model, which has the above-mentioned common feature extraction function; the sub-model of the task feature extraction layer is the second-level sub-model, which has the above-mentioned task feature extraction function; the sub-model of the task output layer is the third-level sub-model, which has the above-mentioned output function.

[0221] It should be noted that the tasks applicable to the first-level sub-model, the second-level sub-model and the third-level sub-model are nested level by level. The first-level sub-model is applicable to all tasks in a task group, the second-level sub-model is applicable to at least one task in the task group, and the third-level sub-model is applicable to one task in the at least one task.

[0222] Optionally, since the first-level sub-model and the second-level sub-model are applicable to more tasks, the first communication device can store the first-level sub-model and / or the second-level sub-model, so there is no need to receive parameters for constructing the first-level sub-model and / or the second-level sub-model, thereby reducing signaling overhead.

[0223] The further description of the hierarchical nesting of the tasks applicable to the first-level sub-model, the second-level sub-model, and the third-level sub-model is as follows: the first-level sub-model can extract a first feature from the input data corresponding to a task group, and the first feature is applicable to all tasks in the task group. Afterwards, the first-level sub-model outputs the first feature to the second-level sub-model, and the second-level sub-model extracts a second feature from the first feature, and the second feature is applicable to at least one task in the task group. Furthermore, the second-level sub-model outputs the second feature to the third-level sub-model, and the third-level sub-model obtains a prediction result based on the second feature, and the prediction result is applicable to one task in the at least one task.

[0224] For example, a task group includes a positioning task and a motion trajectory prediction task. The input data corresponding to this task group is CSI. That is to say, for all tasks in this task group, the input data of the AI ​​model is CSI.

[0225] Suppose the AI model obtained by cascading the first-level sub-model, the second-level sub-model, and the third-level sub-model is an AI model applicable to the positioning task. When implementing the positioning task, first, input the CSI into the first-level sub-model of the AI model, and the first-level sub-model extracts features from the CSI to obtain channel information features. Among them, extracting features from the CSI is, for example, dimensionality reduction of the CSI or extraction of multipath information. Then, the first-level sub-model outputs the channel information features to the second-level sub-model, and the second-level sub-model extracts location-related features, such as location features, from the channel information features. Furthermore, the second-level sub-model outputs the location-related features to the third-level sub-model, and the third-level sub-model predicts the positioning result, such as outputting the terminal coordinates, from the location-related features.

[0226] If the target task is a moving trajectory prediction task, and at least one task applicable to the third-level sub-model does not include the moving trajectory prediction task, the first communication device can switch the sub-model of the task output layer to the target sub-model. In this way, the first-level sub-model, the second-level sub-model, and the target sub-model are cascaded to form an AI model. Then, when implementing the moving trajectory prediction task, first, input the CSI into the first-level sub-model of the AI model, and the first-level sub-model extracts features from the CSI to obtain channel information features. Then, the first-level sub-model outputs the channel information features to the second-level sub-model, and the second-level sub-model extracts moving trajectory prediction-related features, such as location features, from the channel information features. Furthermore, the second-level sub-model outputs the moving trajectory prediction-related features to the third-level sub-model, and the third-level sub-model predicts the moving trajectory of the object, such as outputting the moving direction of the terminal, from the moving trajectory prediction-related features.

[0227] In the above example, whether it is for the positioning task or the moving trajectory prediction task, the data input to the AI model is CSI, that is, the input data for the positioning task and the moving trajectory prediction task in the same task group is of the same type. And whether it is for the positioning task or the moving trajectory prediction task, the first-level sub-model extracts channel information features from the input CSI. Therefore, it can be said that the first-level sub-model has a common feature extraction function related to the task group.

[0228] Referring to Example 7 for task identifiers in the above text, taking the first-level sub-model applicable to task group A1, the second-level sub-model applicable to sub-task group B1 in task group A1, and the third-level sub-model applicable to task 1 in sub-task group B1 as an example, when a task switch occurs, the following several switching scenarios may exist:

[0229] Scenario 5, task switching within subtask group B1. For example, the initial task is task 1 and the target task is task 2, where both task 1 and task 2 belong to subtask group B1. In this scenario, the target hierarchy includes the task output layer, and the terminal can determine the target sub-model 3 of the task output layer and switch the sub-model of the task output layer to the target sub-model 3.

[0230] Scenario 6, task switching between subtask group B1 and subtask group B2. For example, the initial task is task 1, which belongs to subtask group B1, and the target task is task 3, which belongs to subtask group B2. In this scenario, the target hierarchy includes the task feature extraction layer and the task output layer. The terminal can determine the target sub-model 2 of the task feature extraction layer and the target sub-model 3 of the task output layer, and switch the sub-model of the task feature extraction layer to the target sub-model 2 and the sub-model of the task output layer to the target sub-model 3.

[0231] Scenario 7, task switching between task group A1 and task group A2. Referring to Examples 7 and 8 for task identifiers in the above text, the initial task is task 1, which belongs to subtask group B1 in task group A1, and the target task is 5, which belongs to subtask group B3 in task group A2. In this scenario, the target hierarchy includes the common feature extraction layer, the task feature extraction layer, and the task output layer. The terminal can obtain the target sub-model 1 of the common feature extraction layer, the target sub-model 2 of the task feature extraction layer, and the target sub-model 3 of the task output layer, and switch the sub-model of the common feature extraction layer to the target sub-model 1, the sub-model of the task feature extraction layer to the target sub-model 2, and the sub-model of the task output layer to the target sub-model 3.

[0232] The process of triggering model switching based on task switching is similar to the description of the above method 800 and will not be elaborated here.

[0233] In the above method 800, the terminal initiates a switch of the network coverage area and the terminal performs model switching. In addition, the following situations are also included:

[0234] Situation 1, the base station is a fixed base station, that is, the position of the base station is fixed and immovable. In this case, when the terminal initiates a switch of the network coverage area, the base station can receive the identifier of the target object from the terminal and determine the target sub-model based on the identifier of the target object and then perform model switching.

[0235] Situation 2, the base station is a movable base station, such as a drone base station or a vehicle-mounted base station, etc. In this case, the base station can initiate a switch of the network coverage area, and the terminal can determine the target sub-model based on the identifier of the network coverage area sent by the base station and perform model switching.

[0236] Case 3: The base station is a mobile base station. The base station can initiate a handover of the network coverage area and determine the target sub-model based on the identifier of the target network coverage area, and then perform model switching.

[0237] When switching tasks, the base station is peer to the terminal, and both the terminal and the base station switch the sub-model of the target layer.

[0238] For the specific method of determining the target sub-model and performing model switching, reference can be made to the description in the foregoing text, which will not be elaborated here.

[0239] It should be understood that the magnitudes of the sequence numbers of the above processes do not imply the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0240] In the foregoing text, in combination with Figures 6 to 12 , the model switching method according to the embodiments of the present application has been described in detail. Next, in combination with Figure 13 and Figure 14 , the communication device according to the embodiments of the present application will be described in detail.

[0241] Figure 13 FIG. is a schematic block diagram of a communication device 1300 provided by an embodiment of the present application. The device 1300 includes: a processing module 1310. Optionally, the device 1300 includes a transceiver module 1320.

[0242] The processing module 1310 is used for data processing. The transceiver module 1320 can implement corresponding communication functions. The transceiver module 1320 can also be referred to as a communication interface or a communication module.

[0243] Optionally, the device 1300 may further include a storage module, which can be used to store data and / or store computer programs or instructions. The processing module 701 can read the computer programs / instructions and / or data in the storage module, so that the device 1300 can implement the above method embodiments.

[0244] The device 1300 can be used to perform the actions executed by the first communication device in the above method embodiments. The device 1300 can be the first communication device or a component configured in the first communication device. The processing module 1310 is used to perform the operations related to the processing on the side of the first communication device in the above method embodiments. The transceiver module 1320 is used to perform the operations related to the reception on the side of the first communication device in the above method embodiments.

[0245] Optionally, the transceiver module 1320 may include a sending module and a receiving module. The sending module is used to perform the sending operation in the above method embodiments. The receiving module is used to perform the receiving operation in the above method embodiments.

[0246] It should be noted that the device 1300 may include a sending module and not include a receiving module. Alternatively, the device 1300 may include a receiving module and not include a sending module. Specifically, it depends on whether the above-described solution executed by the device 1300 includes a sending action and a receiving action.

[0247] Optionally, the device 1300 is used to execute the above Figure 6 or Figure 8 actions performed by the first communication device in the illustrated embodiment. Specifically, reference may be made to the relevant descriptions in the above Figure 6 or Figure 8 illustrated embodiment, which will not be elaborated here.

[0248] In a possible embodiment, the device 1300 is used to execute the following solution:

[0249] The processing module 1310 is used to: determine an AI model, where the AI model includes multiple levels of sub-models, and each level of sub-model in the multiple levels of sub-models is applicable to at least one object, and the object is a network coverage area or a task; obtain an identifier of the target object; based on the identifier of the target object, determine a target sub-model corresponding to the target object at the corresponding level in the multiple levels of sub-models, where the target sub-model is applicable to the target object; and switch the sub-model at the corresponding level in the multiple levels of sub-models corresponding to the target object to the target sub-model.

[0250] Optionally, the transceiver module 1320 is used to: receive a first message, where the first message indicates parameters for constructing the AI model, a hierarchical structure of the AI model, and at least one object applicable to each level of sub-model, and the multiple levels of sub-models are determined from the AI model based on the hierarchical structure of the AI model.

[0251] Optionally, the hierarchical structure of the AI model indicates a starting neural network layer and an ending neural network layer of each level of sub-model in the AI model.

[0252] Optionally, the processing module 1310 is used to: based on the identifier of the target object, determine whether at least one object applicable to the sub-model at the corresponding level in the multiple levels of sub-models corresponding to the target object includes the target object; in the case where at least one object applicable to the sub-model at the corresponding level in the multiple levels of sub-models corresponding to the target object does not include the target object, obtain parameters for constructing the target sub-model; and based on the parameters for constructing the target sub-model, construct the target sub-model.

[0253] Optionally, the parameters for constructing the target sub-model are carried by the following messages: RRC message, MAC CE, DCI, or UCI.

[0254] Optionally, the identifier of the target object is carried in a handover message, and the handover message is used to indicate a handover to the target object.

[0255] Optionally, the multi-level sub-model includes a multi-level sub-model obtained by dividing the AI model based on network coverage areas of multiple different granularities.

[0256] Optionally, the object is a network coverage area, and the network coverage areas of multiple different granularities are: the network coverage area of a cell group, the network coverage area of a cell, and the network coverage area of a beam. The multi-level sub-model includes: a first-level sub-model, a second-level sub-model, and a third-level sub-model. The network coverage area applicable to the first-level sub-model is the network coverage area of the cell group. The network coverage area applicable to the second-level sub-model is the network coverage area of at least one cell in the cell group. The network coverage area applicable to the third-level sub-model is the network coverage area of at least one beam in the at least one cell.

[0257] Optionally, the storage module is used to: store the first-level sub-model and / or the second-level sub-model.

[0258] Optionally, the identifier of the target object includes a cell group identifier, a cell identifier, and a beam identifier.

[0259] Optionally, the processing module 1310 is used to: train / evaluate the sub-model of the level corresponding to the first network coverage area in the multi-level sub-model based on the data collected in the first network coverage area.

[0260] Optionally, the processing module 1310 is used to: label the data collected in the first network coverage area with the identifier of the first network coverage area.

[0261] Optionally, the multi-level sub-model includes a multi-level sub-model obtained by dividing the AI model based on multiple data processing functions, and the multiple data processing functions are the functions provided by the AI model based on the input data.

[0262] Optionally, the object is a task, and the multiple data processing functions are: a feature extraction function related to a task group corresponding to the input data, a feature extraction function related to at least one task in the task group, and an output function related to one task in the at least one task. The multi-level sub-model includes: a first-level sub-model, a second-level sub-model, and a third-level sub-model. The first-level sub-model is applicable to the task group. The second-level sub-model is applicable to the at least one task. The third-level sub-model is applicable to one task in the at least one task.

[0263] Optionally, the storage module is used to: store the first-level sub-model and / or the second-level sub-model.

[0264] Optionally, the identifier of the target object includes the identifier of the task group to which the target object belongs.

[0265] In this embodiment, the device 1300 may specifically be the first communication device in the above method 600, and the functions of the first communication device in the above method 600 may be integrated into the device 1300. The above functions may be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions. For example, the above transceiver module may be a communication interface, such as a transceiver interface. The device 1300 may be used to execute each process and / or step corresponding to the first communication device in the above method 600.

[0266] In another possible embodiment, the device 1300 is used to execute the following solution:

[0267] The transceiver module 1320 is used to: send a model request message, where the model request message is used to request an AI model.

[0268] The transceiver module 1320 is further used to: receive a model response message, where the model response message indicates the parameters for constructing the AI model, the hierarchical structure of the AI model, and at least one object applicable to each level of sub-model.

[0269] The transceiver module 1320 is further used to: send a handover message. Alternatively, the transceiver module 1320 is further used to: receive a handover message. The handover message is used to indicate a handover to a target network coverage area.

[0270] The transceiver module 1320 is further used to: receive the parameters for constructing the target sub-model.

[0271] The processing module 1310 is used to: perform model switching.

[0272] In this embodiment, the device 1300 may specifically be the first communication device (the first communication device is, for example, a terminal) in the above method 800, and the functions of the first communication device (the first communication device is, for example, a terminal) in the above method 800 may be integrated into the device 1300. The above functions may be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions. For example, the above transceiver module may be a communication interface, such as a transceiver interface. The device 1300 may be used to execute each process and / or step corresponding to the first communication device (the first communication device is, for example, a terminal) in the above method 800.

[0273] In another possible embodiment, the device 1300 is used to execute the following solution:

[0274] The transceiver module 1320 is used to: receive a model request message, where the model request message is used to request an AI model.

[0275] The transceiver module 1320 is further configured to: send a model response message, where the model response message indicates parameters for constructing the AI model, a hierarchical structure of the AI model, and at least one object applicable to each level of sub - models.

[0276] The transceiver module 1320 is further configured to: receive a handover message. Alternatively, the transceiver module 1320 is further configured to: send a handover message. The handover message is used to indicate a handover to a target network coverage area.

[0277] The transceiver module 1320 is further configured to: determine whether to send parameters for constructing a target sub - model to a terminal based on an identifier of the target network coverage area.

[0278] It should be understood that the specific processes for each module to execute the above - mentioned corresponding processes have been described in detail in the above - mentioned method embodiments. For the sake of brevity, they will not be elaborated here.

[0279] The processing module 1310 in the above - mentioned embodiments can be implemented by at least one processor or processor - related circuits. The transceiver module 1320 can be implemented by a transceiver or transceiver - related circuits. The transceiver module 1320 can also be referred to as a communication module or a communication interface. The storage module can be implemented by at least one memory.

[0280] In this embodiment, the apparatus 1300 can specifically be the second communication apparatus (the second communication apparatus is, for example, a base station) in the above - mentioned method 800, and the functions of the second communication apparatus (the second communication apparatus is, for example, a base station) in the above - mentioned method 800 can be integrated in the apparatus 1300. The above - mentioned functions can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above - mentioned functions. For example, the above - mentioned transceiver module can be a communication interface, such as a transceiver interface. The apparatus 1300 can be used to execute each process and / or step corresponding to the second communication apparatus (the second communication apparatus is, for example, a base station) in the above - mentioned method 800.

[0281] The apparatus 1300 is, for example Figure 3 a RAN node, a terminal, a core network device, or other network devices in, and can also be a component (such as a chip) of these devices, for implementing the method described in the above - mentioned method embodiments.

[0282] Figure 14 is a schematic block diagram of another communication apparatus 1400 provided by an embodiment of the present application. It can be understood that the apparatus 1400 includes, for example, modules, units, elements, circuits, or interfaces, etc., which are appropriately configured together to execute the method of the present application. The apparatus 1400 can be Figure 3RAN nodes, terminals, core network devices, or other network devices in [the context], or components (such as chips) in these devices, can also be used to implement the methods described in the above method embodiments. Device 1400 includes one or more processors 111. Processor 111 can be a general-purpose processor or a dedicated processor, etc. For example, it can be a baseband processor or a central processing unit. The baseband processor can be used to process communication protocols and communication data, and the central processing unit can be used to control communication devices (such as network devices, terminals, or chips, etc.), execute software programs, and process data of software programs.

[0283] Optionally, in one design, processor 111 can include program 113 (sometimes also referred to as code, computer program, or instruction), and the program 113 can be run on processor 111, enabling device 1400 to execute the methods described in the above embodiments.

[0284] Optionally, device 1400 can include one or more memories 112, on which there is program 114 (sometimes also referred to as code, computer program, or instruction), and program 114 can be run on processor 111, enabling device 1400 to execute the methods described in the above method embodiments.

[0285] Optionally, AI modules 117, 118 can be included in processor 111 and / or memory 112, and the AI modules are used to implement AI-related functions. The AI modules can be implemented in a software, hardware, or a combination of software and hardware manner. For example, the AI module can include a RIC module. For example, the AI module can be a near-real-time RIC or a non-real-time RIC.

[0286] Optionally, data can also be stored in processor 111 and / or memory 112. The processor and the memory can be set separately or integrated together.

[0287] Optionally, device 1400 can also include a transceiver 115 and / or an antenna 116. Processor 111 is sometimes also referred to as a processing unit, which controls communication device 1400 (such as a network device or a terminal). Transceiver 115 is sometimes also referred to as a transceiver unit, transceiver, transceiver circuit, or transceiver, etc., and is used to implement the transceiver function of the communication device through antenna 116.

[0288] This application also provides a device 1500, and device 1500 can be a terminal, a processor in a terminal, or a chip. Device 1500 can be used to perform the operations executed by the first communication device (the first communication device is, for example, a terminal) in the above method embodiments.

[0289] When device 1500 is a terminal, Figure 15A schematic structural diagram of a simplified terminal is shown. As Figure 15 shown, the terminal includes a processor, a memory, and a transceiver. The memory can store computer program code. The transceiver includes a transmitter 1531, a receiver 1532, a radio frequency circuit ( Figure 15 not shown in the figure), an antenna 1533, and an input / output device ( Figure 15 not shown in the figure).

[0290] The processor is mainly used to process communication protocols and communication data; control the terminal, execute software programs, and process data of software programs, etc.

[0291] The memory is mainly used to store software programs and data.

[0292] The radio frequency circuit is mainly used for the conversion between baseband signals and radio frequency signals and the processing of radio frequency signals.

[0293] The antenna is mainly used to transmit and receive radio frequency signals in the form of electromagnetic waves.

[0294] The input / output device may include a touch screen, a display screen, or a keyboard, etc. The input / output device is mainly used to receive data input by the user and output data to the user. It should be noted that some types of terminals may not have an input / output device.

[0295] When data needs to be sent, after the processor performs baseband processing on the data to be sent, it outputs a baseband signal to the radio frequency circuit. Then, the radio frequency circuit performs radio frequency processing on the baseband signal and sends the radio frequency signal outwards in the form of electromagnetic waves through the antenna. When data is sent to the terminal, the radio frequency circuit receives the radio frequency signal through the antenna. The radio frequency circuit converts the radio frequency signal into a baseband signal and outputs the baseband signal to the processor. The processor converts the baseband signal into data and processes the data. For ease of explanation, Figure 15 only one memory, processor, and transceiver are shown in the figure. In an actual terminal product, there may be one or more processors and one or more memories. The memory may also be referred to as a storage medium or a storage device, etc. The memory may be set independently of the processor or integrated with the processor. The embodiments of the present application do not limit this.

[0296] In the embodiments of the present application, the antenna and the radio frequency circuit with transceiver functions can be regarded as the transceiver module of the terminal, and the processor with processing functions can be regarded as the processing module of the terminal.

[0297] As Figure 15As shown, the terminal includes a processor 1510, a memory 1520, and a transceiver 1530. The processor 1510 may also be referred to as a processing unit, a processing board, a processing module, or a processing device, etc. The transceiver 1530 may also be referred to as a transceiver unit, a transceiver, or a transceiver device, etc.

[0298] Optionally, the devices in the transceiver 1530 for implementing the receiving function are regarded as a receiving module, and the devices in the transceiver 1530 for implementing the sending function are regarded as a sending module, that is, the transceiver 1530 includes a receiver and a transmitter. The transceiver may sometimes also be referred to as a transceiver, a transceiver module, or a transceiver circuit, etc. The receiver may sometimes also be referred to as a receiver, a receiving module, or a receiving circuit, etc. The transmitter may sometimes also be referred to as a transmitter, a transmitting module, or a transmitting circuit, etc.

[0299] The processor 1510 is used to execute the processing actions of the first communication device in the above Figure 6 or Figure 8 shown embodiments. The transceiver 1530 is used to execute the transceiver actions of the first communication device in the above Figure 6 or Figure 8 shown embodiments.

[0300] It should be understood that Figure 15 merely by way of example and not limitation, the above terminal including a transceiver module and a processing module may not depend on the Figure 13 , Figure 14 or Figure 15 shown structure.

[0301] When the device 1500 is a chip, in a possible design, the chip includes a processor, a memory, and a transceiver. Among them, the transceiver may be an input / output circuit or a communication interface. The processor may be an integrated processing module, a microprocessor, or an integrated circuit on the chip. The sending operation of the first communication device in the above method embodiments may be understood as the output of the chip, and the receiving operation of the first communication device or the second communication device in the above method embodiments may be understood as the input of the chip.

[0302] When the device 1500 is a chip, in another possible design, the transceiver of the chip may be an input / output interface, and the memory is external to the chip.

[0303] This application also provides a device 1600. The device 1600 may be a network device or a chip. The device 1600 may be used to execute the operations performed by the first communication device (the first communication device is, for example, a base station) in the above Figure 6 , or the operations performed by the second communication device (the second communication device is, for example, a base station) in the above Figure 8 .

[0304] When the device 1600 is a network device, for example, a base station.Figure 16 A simplified schematic diagram of a base station structure is shown. The base station includes a 1610 part, a 1620 part, and a 1630 part.

[0305] The 1610 part is mainly used for baseband processing and controlling the base station, etc.; the 1610 part is usually the control center of the base station and can usually be called a processor, which is used to control the base station to execute the processing operations on the side of the first communication device or the second communication device in the above method embodiments.

[0306] The 1620 part is mainly used for storing computer program codes and data.

[0307] The 1630 part is mainly used for receiving and transmitting radio frequency signals and converting radio frequency signals and baseband signals; the 1630 part can usually be called a transceiver module, a transceiver, a transceiver circuit, or a transceiver, etc. The transceiver module of the 1630 part can also be called a transceiver or a transceiver, etc., and it includes an antenna 1633 and a radio frequency circuit ( Figure 16 not shown in the figure), where the radio frequency circuit is mainly used for radio frequency processing. Optionally, the devices used to implement the receiving function in the 1630 part can be regarded as a receiver, and the devices used to implement the transmitting function can be regarded as a transmitter, that is, the 1630 part includes a receiver 1632 and a transmitter 1631. The receiver can also be called a receiving module, a receiver, or a receiving circuit, etc., and the transmitter can be called a transmitting module, a transmitter, or a transmitting circuit, etc.

[0308] The 1610 part and the 1620 part can include one or more single boards, and each single board can include one or more processors and one or more memories. The processor is used to read and execute the programs in the memory to implement the baseband processing function and the control of the base station. If there are multiple single boards, the single boards can be interconnected with each other to enhance the processing ability. As an optional implementation manner, it can also be that multiple single boards share one or more processors, or multiple single boards share one or more memories, or multiple single boards share one or more processors at the same time.

[0309] For example, in one implementation manner, the transceiver module of the 1630 part is used to execute the transceiver-related processes performed by the first communication device or the second communication device in the above embodiments. The processor of the 1610 part is used to execute the processing-related processes performed by the first communication device or the second communication device in the above embodiments.

[0310] It should be understood that Figure 16 only as an example and not a limitation, the above network device including a processor, a memory, and a transceiver may not depend on Figure 13 、 Figure 14 or Figure 16 the structure shown.

[0311] When the device 1600 is a chip, in a possible design, the chip includes a transceiver, a memory, and a processor. Among them, the transceiver can be an input / output circuit (or input / output interface), a communication interface; the processor is the processor integrated on the chip, or a microprocessor, or an integrated circuit. The sending operation of the first communication device or the second communication device in the above method embodiments can be understood as the output of the chip, and the receiving operation of the first communication device or the second communication device in the above method embodiments can be understood as the input of the chip.

[0312] When the device 1500 is a chip, in another possible design, the transceiver of the chip can be an input / output interface, and the memory is external to the chip.

[0313] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program (which can also be called code, or instruction). When it runs on a computer, it causes the computer to execute the method performed by the first communication device or the second communication device in the above method embodiments.

[0314] An embodiment of the present application also provides a computer program product including a computer program or instruction. When the computer program or instruction is executed by a computer, it causes the computer to implement the method performed by the first communication device or the second communication device in the above method embodiments.

[0315] An embodiment of the present application also provides a communication system, which includes the first communication device and the second communication device in the above embodiments. The first communication device is used to perform part or all of the operations performed by the first communication device in the above method embodiments, and the second communication device is used to perform part or all of the operations performed by the second communication device in the above method embodiments.

[0316] An embodiment of the present application also provides a chip device, including a processor, which is used to call the computer program or instruction stored in the memory, so that the processor executes the method provided in the above embodiments.

[0317] In a possible implementation manner, the input of the chip device corresponds to the receiving operation in any one of the above embodiments, and the output of the chip device corresponds to the sending operation in any one of the above embodiments.

[0318] Optionally, the processor is coupled to the memory through an interface.

[0319] Optionally, the chip device further includes a memory, and the memory stores a computer program or instruction.

[0320] Among them, the processor mentioned anywhere above can be a general-purpose central processing unit, a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of a program for any one of the methods provided in the above embodiments. The memory mentioned anywhere above can be a read-only memory (ROM) or other types of static storage devices that can store static information and computer programs or instructions, a random access memory (RAM), etc.

[0321] Those skilled in the art can clearly understand that for the sake of convenience and conciseness of description, the explanations and beneficial effects of the relevant content in any of the above-mentioned devices can be referred to the corresponding method embodiments provided above, and will not be elaborated here.

[0322] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0323] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0324] In addition, the functional units in each embodiment of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0325] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the part that essentially contributes to the technical solution of this application, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes a number of computer programs or instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical discs that can store program codes.

[0326] As described above, the above embodiments are only used to illustrate the technical solutions of this application, rather than to limit them; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of various embodiments of this application.

Claims

1. A model switching method, characterized in that, Including: Determine an artificial intelligence (AI) model, where the AI model includes multiple levels of sub-models, and each level of sub-model in the multiple levels of sub-models applies to at least one object; Obtain an identifier of a target object; Based on the identifier of the target object, determine a target sub-model of the level corresponding to the target object, where the target sub-model applies to the target object; Switch the sub-model of the level corresponding to the target object in the multiple levels of sub-models to the target sub-model.

2. The method according to claim 1, wherein Before determining the AI model, the method further includes: Receive a first message, where the first message indicates parameters for constructing the AI model, a hierarchical structure of the AI model, and at least one object to which each level of sub-model applies, and the multiple levels of sub-models are determined from the AI model based on the hierarchical structure of the AI model.

3. The method according to claim 2, wherein The hierarchical structure of the AI model indicates a starting neural network layer and an ending neural network layer of each level of sub-model in the AI model.

4. The method according to any one of claims 1 to 3, characterized in that, The determining, based on the identifier of the target object, a target sub-model of the level corresponding to the target object includes: Based on the identifier of the target object, determine whether at least one object to which the sub-model of the level corresponding to the target object in the multiple levels of sub-models applies includes the target object; In a case where at least one object to which the sub-model of the level corresponding to the target object in the multiple levels of sub-models applies does not include the target object, obtain parameters for constructing the target sub-model; Based on the parameters for constructing the target sub-model, construct the target sub-model.

5. The method according to claim 4, characterized in that, The parameters for constructing the target sub-model are carried by the following message: Radio Resource Control (RRC) message, Medium Access Control Control Element (MAC CE), Downlink Control Information (DCI), or Uplink Control Information (UCI).

6. The method according to any one of claims 1 to 5, characterized in that, The identifier of the target object is carried in a handover message, and the handover message is used to indicate a handover to the target object.

7. The method according to any one of claims 1 to 6, characterized in that The multiple levels of sub-models include multiple levels of sub-models obtained by dividing the AI model based on network coverage areas of multiple different granularities.

8. The method according to claim 7, wherein The object is a network coverage area, and the multiple different granularities of network coverage areas are: a network coverage area of a cell group, a network coverage area of a cell, and a network coverage area of a beam; The multiple levels of sub-models include: a first-level sub-model, a second-level sub-model, and a third-level sub-model. The network coverage area to which the first-level sub-model applies is the network coverage area of the cell group, the network coverage area to which the second-level sub-model applies is the network coverage area of at least one cell in the cell group, and the network coverage area to which the third-level sub-model applies is the network coverage area of at least one beam in the at least one cell.

9. The method according to claim 8, characterized in that The method further includes: Store the first-level sub-model and / or the second-level sub-model.

10. The method according to claim 8 or 9, characterized in that The identifier of the target object includes a cell group identifier, a cell identifier, and a beam identifier.

11. The method according to any one of claims 7 to 10, characterized in that, The method further includes: Based on data collected in a first network coverage area, train or evaluate the sub-model of the level corresponding to the first network coverage area in the multiple levels of sub-models.

12. The method according to claim 11, wherein Before training / evaluating the sub-model of the level corresponding to the first network coverage area in the multi-level sub-model based on the data collected in the first network coverage area, the method further includes: Marking the data collected in the first network coverage area with the identifier of the first network coverage area.

13. The method according to any one of claims 1 to 6, characterized in that, The multi-level sub-model includes a multi-level sub-model obtained by dividing the AI model based on multiple data processing functions, and the multiple data processing functions are functions provided by the AI model based on input data.

14. The method according to claim 13, wherein The object is a task, and the multiple data processing functions are: a feature extraction function related to a task group corresponding to the input data, a feature extraction function related to at least one task in the task group, and an output function related to one task in the at least one task; The multi-level sub-model includes: a first-level sub-model, a second-level sub-model, and a third-level sub-model. The first-level sub-model is applicable to the task group, the second-level sub-model is applicable to the at least one task, and the third-level sub-model is applicable to one task in the at least one task.

15. The method according to claim 14, characterized in that The method further includes: Storing the first-level sub-model and / or the second-level sub-model.

16. The method according to claim 14 or 15, characterized in that, The identifier of the target object includes the identifier of the task group to which the target object belongs.

17. A communication device, characterized in that, Including a module for implementing the method according to any one of claims 1 to 16.

18. A communication device, characterized in that, Including a processor, the processor is configured to execute a computer program or instruction in a memory to implement the method according to any one of claims 1 to 16.

19. A computer-readable storage medium, characterized in that, For storing a computer program or instruction, when the computer program or instruction runs on a computer, the method according to any one of claims 1 to 16 is executed.

Images