Communication method and device

Abstract

The invention provides a communication method and device. The method comprises the steps that first information is received, the first information comprises a first identifier and first configuration information, the first identifier is used for identifying a feature, a function or a model, the first configuration information is used for configuring all or part of models associated with N1 features, all or part of models associated with N2 functions or N3 models, and M1, M2, N1, N2 and N3 are all positive integers; according to the first identifier, the first configuration information is applied to the first feature, the first function or the first model, the first feature is at least one of the N1 features, the first function is at least one of the N2 functions, and the first model is at least one of the N3 models.

Description

Technical Field

[0001] This application relates to the field of mobile communication technologies, and in particular, to a communication method and apparatus. Background Art

[0002] Currently, artificial intelligence (AI) / machine learning (ML) has important application potential in many aspects such as complex unknown environment modeling and learning, channel prediction, intelligent signal generation and processing, network state tracking and intelligent scheduling, and network optimization and deployment. It is expected to promote the evolution of future communication paradigms and the transformation of network architectures, and is of great significance and value to the research of 6G technologies.

[0003] The AI / ML technology relies on the computing implementation of AI models. In the applications of some specific scenarios in technical fields such as communication, the number of AI models may be extremely large. Therefore, how to achieve the efficient configuration of AI models is a technical problem to be solved urgently. Summary of the Invention

[0004] To solve the above technical problems, this application provides a communication method and apparatus to achieve the efficient configuration of an AI module.

[0005] In a first aspect, a communication method is provided. This method can be executed by a first communication device. The first communication device can be a terminal device, other devices with terminal device functions, or a chip (or chip system, where the chip system includes a chip) or other functional modules, etc. The chip system or functional module can implement the functions of the terminal device, and the chip system or functional module is, for example, disposed in the terminal device. In the following description, it is taken as an example that this method is executed by the terminal device. The method includes: the terminal device receives first information, where the first information includes a first identifier and first configuration information. The first identifier is used to identify a feature, a function, or a model. The first configuration information is used to configure all or part of the models associated with N1 features, all or part of the models associated with N2 functions, or N3 models. The N1 features correspond to M1 functions, the M1 functions correspond to M2 models, and the M2 models are all or part of the models associated with the N1 features. M1, M2, N1, N2, and N3 are all positive integers; the terminal device applies the first configuration information to a first feature, a first function, or a first model according to the first identifier, where the first feature is at least one of the N1 features, the first function is at least one of the N2 functions, and the first model is at least one of the N3 models.

[0006] Optionally, applying the first configuration information to a first feature, a first function, or a first model means applying the first configuration information to all or part of the functions associated with the first feature, all or part of the models associated with the first function, or the first model.

[0007] Optionally, "associated" can also be understood as "corresponding".

[0008] Optionally, "associated" includes "subordinate".

[0009] In the first aspect, the first information can be used to configure a model. Among them, the first identifier can be used to indicate a feature, a function, or a model, that is, it can indicate that the first configuration information is a configuration at the feature, function, or model level. Correspondingly, the first configuration information is used to configure all or part of the models associated with N1 features, all or part of the models associated with N2 functions, or N3 models. That is to say, the first configuration information can be used to configure all or part of the models associated with the same feature, or the first configuration information can be applied to configure all or part of the models associated with the same function, or the first configuration information can be applied to configure one or more models, that is, there is no need to configure each model separately, which can improve the model configuration efficiency.

[0010] As an implementation manner, for example, if the first identifier indicates a feature, the first configuration information is used to configure all or part of the models associated with N1 features; if the first identifier indicates a function, the first configuration information is used to configure all or part of the models associated with N2 functions; if the first identifier indicates a model, the first configuration information can be used to configure N3 models.

[0011] As a possible implementation manner, the first configuration information can be used for at least one of data measurement or data reporting. Or rather, the first configuration information can include data measurement parameters and / or data reporting parameters. Among them, the data measurement parameters are, for example, measurement object (MO). The data reporting parameters are, for example, reporting configuration (RC).

[0012] As a possible implementation, the first information further includes a second identifier, where the second identifier is used to identify a feature, a function, or a model; the terminal device can also apply the first configuration information to a second feature, a second function, or a second model according to the second identifier, where the second feature is at least one of the N1 features, the second feature is different from the first feature, the second function is at least one of the N2 functions, the second function is different from the first function, the second model is at least one of the N3 models, and the second model is different from the first model. Based on this implementation, the first information can include multiple identifiers, and the multiple identifiers can correspond to different features, functions, or models. The first configuration information can be used to configure the features, functions, or models indicated by the multiple identifiers. Among them, the multiple identifiers can include the first identifier and the second identifier. Therefore, the first configuration information can be configured to different features, functions, or models indicated by the multiple identifiers, realizing the efficient configuration of the AI model. The first information can further include more identifiers other than the first identifier and the second identifier, and the first configuration information can be applicable to the features, functions, or models indicated by the multiple identifiers. The present application does not specifically limit this.

[0013] As a possible implementation, the first information further includes a second identifier and second configuration information, where the second identifier is used to identify a feature, a function, or a model, and the second configuration information is used to configure all or part of the models associated with L1 features, all or part of the models associated with L2 functions, or L3 models. The L1 features correspond to K1 functions, the K1 functions correspond to K2 models, and the K2 models are all or part of the models associated with the L1 features. K1, K2, L1, L2, and L3 are all positive integers; the terminal device can also apply the second configuration information to a third feature, a third function, or a third model according to the second identifier, where the third feature is at least one of the L1 features, the third function is at least one of the L2 functions, and the third model is at least one of the L3 models. Based on this implementation, the first information can include multiple identifiers and multiple configuration information, and the multiple identifiers can correspond to different features, functions, or models; the multiple configuration information can respectively configure the features, functions, or models indicated by different identifiers, realizing the efficient configuration of the AI model. For example, the multiple identifiers include the first identifier and the second identifier, and the multiple configuration information includes the first configuration information and the second configuration information. The first information can further include more identifiers other than the first identifier and the second identifier, and more configuration information other than the first configuration information and the second configuration information. The present application does not specifically limit this.

[0014] As a possible implementation, the first configuration information is used to configure all or part of the models associated with the N1 features, and the first information further includes third configuration information, which is used to configure all or part of the models associated with the N1 features. Based on this implementation, the first information can include multiple configuration information, such as including the first configuration information and the third configuration information. The first configuration information and the third configuration information can respectively be applicable to part or all of the models associated with the features or functions indicated by the first identifier, realizing the efficient configuration of the AI model.

[0015] As a possible implementation, the terminal device can, according to the first identifier, configure the first part of the models associated with the first feature with the first configuration information, and configure the second part of the models associated with the first feature with the third configuration information; wherein, the first part of the models is different from the second part of the models. Based on this implementation, the first information can include multiple configuration information corresponding to the first identifier, including the first configuration information and the third configuration information. Among them, the multiple configuration information can be respectively used to configure part of the models in the features or functions indicated by the first identifier to realize the efficient configuration of the AI model. Which models the multiple configuration information is respectively applicable to can be determined by the terminal device. The first information can also include more configuration information other than the first configuration information and the third configuration information. This application does not specifically limit it. The multiple configuration information can be respectively applicable to part of the models in the features or functions indicated by the first identifier.

[0016] As a possible implementation, before receiving the first information, the terminal device can also send a first request, which is used to request to configure the N1 features, the N2 functions or the N3 models; and / or, to request to provide P1 configurations for the N1 features, P2 configurations for the N2 functions or P3 configurations for the N3 models. Based on this implementation, the terminal device can send a first request to the access network device to provide a model configuration request of the terminal device, so that the access network device provides accurate and efficient model configuration. The model configuration request can include the terminal device's requirements for the configuration level and / or the number of different levels of configuration information.

[0017] As a possible implementation, the first configuration information is used to configure all or part of the models associated with N1 features, all or part of the models associated with N2 functions, or N3 models, including: the first configuration information is used to configure all or part of the models associated with the N1 features in the first stage, all or part of the models associated with the N2 functions in the first stage, or the N3 models in the first stage; wherein, the first stage includes at least one of the following: a training stage, an inference stage, or a monitoring stage. Based on this implementation, the model configuration can be determined according to the training stage of the model to achieve efficient configuration of the AI model. Among them, models in different training stages can adopt the same or different configurations.

[0018] As a possible implementation, the first configuration information is used to configure all or part of the models associated with N1 features, all or part of the models associated with N2 functions, or N3 models, including: the first configuration information is used to configure all or part of the models associated with the N1 features of the first requirement, all or part of the models associated with the N2 functions of the first requirement, or the N3 models of the first requirement; wherein, the first requirement includes at least one of the following: a high-precision requirement, a medium-precision requirement, or a low-precision requirement. Based on this implementation, the model configuration can be determined according to the precision requirement of the model to achieve efficient configuration of the AI model. Among them, models with different precision requirements can adopt the same or different configurations.

[0019] In a second aspect, a communication method is provided. This method can be executed by a second communication device. The second communication device can be an access network device, other devices with access network device functions, or a chip (or a chip system, the chip system includes a chip) or other functional modules, etc. The chip system or functional module can implement the functions of the access network device, and the chip system or functional module is, for example, disposed in the access network device. In the following introduction, it is taken as an example that this method is executed by the access network device. The method includes: the access network device determines and sends first information, the first information includes a first identifier and first configuration information, the first identifier is used to identify a feature, a function, or a model, the first configuration information is used to configure all or part of the models associated with N1 features, all or part of the models associated with N2 functions, or N3 models, the N1 features correspond to M1 functions, the M1 functions correspond to M2 models, and the M2 models are all or part of the models associated with the N1 features. M1, M2, N1, N2, and N3 are all positive integers.

[0020] As a possible implementation, the first configuration information can be used for at least one of data measurement or data reporting.

[0021] As a possible implementation, the first information further includes a second identifier, where the second identifier is used to identify a feature, a function, or a model; the first configuration information is applied to a second feature, a second function, or a second model, where the second feature is at least one of the N1 features, the second feature is different from the first feature, the second function is at least one of the N2 functions, the second function is different from the first function, the second model is at least one of the N3 models, and the second model is different from the first model.

[0022] As a possible implementation, the first information further includes a second identifier and second configuration information, where the second identifier is used to identify a feature, a function, or a model, and the second configuration information is used to configure all or part of the models associated with L1 features, all or part of the models associated with L2 functions, or L3 models. The L1 features correspond to K1 functions, the K1 functions correspond to K2 models, and the K2 models are all or part of the models associated with the L1 features. K1, K2, L1, L2, and L3 are all positive integers; the second configuration information is used to configure a third feature, a third function, or a third model, where the third feature is at least one of the L1 features, the third function is at least one of the L2 functions, and the third model is at least one of the L3 models.

[0023] As a possible implementation, the first configuration information is used to configure all or part of the models associated with the N1 features, and the first information further includes third configuration information, where the third configuration information is used to configure all or part of the models associated with the N1 features.

[0024] As a possible implementation, the first configuration information is used for the first part of the models associated with the first feature, and the third configuration information is used for the second part of the models associated with the first feature; where the first part of the models is different from the second part of the models.

[0025] As a possible implementation, before receiving the first information, the access network device may further receive a first request, where the first request is used to request to configure the N1 features, the N2 functions, or the N3 models; and / or, to request to provide P1 configurations for the N1 features, P2 configurations for the N2 functions, or P3 configurations for the N3 models.

[0026] As a possible implementation, the first configuration information is used to configure all or part of the models associated with N1 features, all or part of the models associated with N2 functions, or N3 models, including: the first configuration information is used to configure all or part of the models associated with the N1 features in the first stage, all or part of the models associated with the N2 functions in the first stage, or the N3 models in the first stage; wherein, the first stage includes at least one of the following: training stage, inference stage, or monitoring stage.

[0027] As a possible implementation, the first configuration information is used to configure all or part of the models associated with N1 features, all or part of the models associated with N2 functions, or N3 models, including: the first configuration information is used to configure all or part of the models associated with the N1 features of the first requirement, all or part of the models associated with the N2 functions of the first requirement, or the N3 models of the first requirement; wherein, the first requirement includes at least one of the following: high-precision requirement, medium-precision requirement, or low-precision requirement.

[0028] The beneficial effects of the second aspect and its various possible implementations can be referred to the description of the corresponding beneficial effects in the first aspect, and will not be repeated.

[0029] In a third aspect, a communication device is provided. The device is used to implement the method described in any one of the above first aspect to the second aspect and its any possible implementation. The device is, for example, a terminal device or a chip, etc., or a network device or a chip, etc.

[0030] In an optional implementation, the device may include modules respectively associated with the methods / operations / steps / actions described in any one of the first aspect to the second aspect and its any possible implementation. The module may be a hardware circuit, software, or a combination of hardware circuit and software. In an optional implementation, the device includes a processing unit (sometimes also referred to as a processing module) and a communication unit (sometimes also referred to as a transceiver module, communication module, etc.). The transceiver unit can implement the sending function and the receiving function. When the transceiver unit implements the sending function, it can be referred to as a sending unit (sometimes also referred to as a sending module). When the transceiver unit implements the receiving function, it can be referred to as a receiving unit (sometimes also referred to as a receiving module). The sending unit and the receiving unit may be the same functional module, and this functional module is called the transceiver unit, which can implement the sending function and the receiving function; or, the sending unit and the receiving unit may be different functional modules, and the transceiver unit is a general term for these functional modules.

[0031] Exemplarily, when the device is used to execute the method described in any one of the first aspect to the second aspect, the device may include a communication unit and a processing unit.

[0032] Fourthly, an embodiment of the present application further provides a communication device, including a processor configured to execute a computer program (or computer-executable instructions) stored in a memory. When the computer program (or computer-executable instructions) is executed, the device is caused to execute the method described in any possible implementation manner of any one of the first aspect to the second aspect.

[0033] In a possible implementation, the processor and the memory are integrated together;

[0034] In another possible implementation, the memory is located outside the communication device.

[0035] The communication device further includes a communication interface configured to communicate the communication device with other devices, such as sending or receiving data and / or signals. Exemplarily, the communication interface may be a transceiver, a circuit, a bus, a module, or other types of communication interfaces.

[0036] Fifthly, a computer-readable storage medium is provided, which is used to store a computer program or instructions. When it runs, the method described in any possible implementation manner of any one of the first aspect to the second aspect and the method shown in any possible implementation manner thereof are implemented.

[0037] Sixthly, a computer program containing instructions is provided. When the computer program runs, the method in any possible implementation manner of any one of the above first aspect to the second aspect is implemented.

[0038] Seventhly, a chip system is provided. The chip system includes a logic circuit (or understood as, the chip system includes a processor, and the processor may include a logic circuit, etc.), and may further include an input / output interface. The input / output interface can be used to input messages and can also be used to output messages. The input / output interface can be the same interface, that is, the same interface can implement both the sending function and the receiving function; or, the input / output interface includes an input interface and an output interface. The input interface is used to implement the receiving function, that is, to receive messages; the output interface is used to implement the sending function, that is, to send messages. The logic circuit can be used to execute the operations other than the transceiver function in the method described in any possible implementation manner of any one of the first aspect to the second aspect; the logic circuit can also be used to transmit messages to the input / output interface or receive messages from other communication devices from the input / output interface. The chip system can be used to implement the method described in any possible implementation manner of any one of the first aspect to the second aspect. The chip system can be composed of chips or can include chips and other discrete devices.

[0039] Optionally, the chip system may further include a memory, which can be used to store instructions, and the logic circuit can call the instructions stored in the memory to implement corresponding functions.

[0040] In an eighth aspect, a communication method is provided. The communication method may include the method implemented by the first communication device as shown in the first aspect and any possible implementation manners thereof, and the method implemented by the second communication device as shown in the second aspect and any possible implementation manners thereof.

[0041] In a ninth aspect, a communication system is provided. The communication system may include a first communication device and a second communication device. Among them, the first communication device can be used to implement the method as shown in the first aspect and any possible implementation manners thereof, and the second communication device can be used to implement the method as shown in the second aspect and any possible implementation manners thereof.

[0042] For the technical effects brought by the above third aspect to the ninth aspect, reference may be made to the description of the beneficial effects of the corresponding solutions in the above first aspect to the second aspect, which will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 Schematic diagram of the architecture of a wireless communication system provided by an embodiment of the present application;

[0044] Figure 2 Schematic diagram of a model level provided by an embodiment of the present application;

[0045] Figure 3 Schematic flow chart of a communication method provided by an embodiment of the present application;

[0046] Figure 4 Schematic diagram of the correspondence between configuration information and level information provided by an embodiment of the present application;

[0047] Figure 5 Another schematic diagram of the correspondence between configuration information and level information provided by an embodiment of the present application;

[0048] Figure 6 Schematic diagram of the correspondence between configuration information and stage information provided by an embodiment of the present application;

[0049] Figure 7 Another schematic diagram of the correspondence between configuration information and stage information provided by an embodiment of the present application;

[0050] Figure 8 Schematic diagram of the structure of a communication device provided by an embodiment of the present application;

[0051] Figure 9 Another schematic diagram of the structure of a communication device provided by an embodiment of the present application. Detailed implementation manners

[0052] To facilitate the understanding of the embodiments of the present application, the application scenarios used in the present application will be described by taking the Figure 1 shown communication system architecture as an example. Figure 1 A possible and non-limiting system schematic diagram is shown. As Figure 1 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 network device (such as Figure 1 101a and 101b in Figure 1 , collectively referred to as 110) and at least one terminal device (such as Figure 1 102a - 102j in

[0053] collectively referred to as 102). Other RAN nodes may also be included in the RAN100, for example, wireless relay devices and / or wireless backhaul devices (

[0054] not shown in Figure 1 ). The terminal device 102 is connected to the network device 101 wirelessly. The network device 101 is connected to the core network 200 wirelessly or wiredly. The core network devices in the core network 200 and the network device 101 in the RAN100 may be different physical devices respectively, or may be the same physical device integrating the core network logic function and the radio access network logic function.

[0055] In another communication system to which the embodiments of the present application are applied, it may include a first communication device and a second communication device.

[0056] In an implementation method, the first communication device is a network device or a module for a network device, and the second communication device is a terminal device or a module for a terminal device. Among them, the network device is, for example, an access network device. The first communication device and the second communication device communicate with each other through the air interface.

[0057] In another implementation method, the first communication device is a terminal device or a module for a terminal device, and the second communication device is a network device or a module for a network device. The first communication device and the second communication device communicate with each other through the air interface.

[0058] In another implementation method, the first communication device is a network device or a module for a network device, and the second communication device is a network device or a module for a network device. The first communication device and the second communication device communicate with each other through the air interface or in a wired manner.

[0059] In another implementation method, the first communication device is a terminal device or a module for a terminal device, and the second communication device is a terminal device or a module for a terminal device. The first communication device and the second communication device communicate with each other through the air interface.

[0060] Of course, the first communication device and the second communication device in the embodiments of the present application may also be other types of devices. For example, the first communication device may also be a cloud device or a cloud server, etc., and the second communication device is a cloud device or a cloud server, etc. The present application does not make any limitations in this regard.

[0061] In the implementation of this application, the terminal device is a device with wireless transceiver functions, which may specifically refer to user equipment (UE), access terminal, subscriber unit, user station, mobile station, remote station, remote terminal, mobile device, user terminal, wireless communication device, user agent or user device. The terminal device can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; it can also be deployed on water (such as ships, etc.); it can also be deployed in the air (such as on airplanes, balloons, satellites, etc.). The terminal device can be a cellular phone, mobile phone, tablet (pad), wireless data card, wireless modem, satellite terminal, vehicle (such as cars, bicycles, electric vehicles, airplanes, ships, trains, high-speed rails, etc.)-mounted device, robotic arm, workshop equipment, wearable device (such as smart watches, smart bracelets, pedometers, etc.), drone, robot, intelligent point of sale (POS) machine, customer-premises equipment (CPE), computer with wireless transceiver functions, virtual reality (VR) terminal device, augmented reality (AR) terminal device, terminal device in industrial control, terminal device in self-driving, terminal device in remote medical, terminal device in smart grid, terminal in transportation safety, terminal device in smart city, terminal device in smart home (such as smart home appliances like refrigerators, TVs, air conditioners, electricity meters, etc.). The terminal device can also be other devices with terminal functions. The embodiments of this application do not limit the device form of the terminal. The device for implementing the functions of the terminal device can be the terminal device; it can also be a device capable of supporting the terminal device to implement the functions, such as a chip system. The device can be installed in the terminal device or used in matching with the terminal device. In the embodiments of this application, the chip system can be composed of chips or can also include chips and other discrete devices.

[0062] In the implementation of this application, a network device is a device with wireless transceiver capabilities, used for communicating with terminal devices or other network devices; it can also be a device capable of connecting a terminal device to a wireless network, such as a radio access network (RAN) device or node. The network device in the embodiments of this application can include various forms of base stations, for example: base station, evolved NodeB (eNodeB), next-generation NodeB (gNB), macro base station, micro base station (also known as small station), relay station, access point, a device that implements the base station function in a communication system evolved after the 5th generation (5G) technology, an access point (AP) in a wireless local area network (WLAN) system, an integrated access and backhaul (IAB) node, a transmitting and receiving point (TRP), a transmitting point (TP), a mobile switching center, and a device that undertakes the base station function in device-to-device (D2D), vehicle-to-everything (V2X), and machine-to-machine (M2M) communications, etc. It can also include network devices in a non-terrestrial network (NTN) communication system, that is, it can be deployed on a high-altitude platform or satellite. In some possible scenarios, different network devices respectively implement some functions of the base station. For example, the network device 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 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 radio frequency unit, for example, included in a remote radio unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH). It can be understood that the network device can be a CU node, or a DU node, or a device including a CU node and a DU node.In addition, the CU can be classified as a network device in the radio access network (RAN), or the CU can be classified as a network device in the core network (CN), without any limitation here.

[0063] 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 an open RAN (ORAN) system, the CU can also be referred to as an O-CU (open CU), the DU can also be referred to as an O-DU, the CU-CP can also be referred to as an O-CU-CP, the CU-UP can also be referred to as an O-CU-UP, and the RU can also be referred to as an O-RU. For the sake of convenient description, the CU, CU-CP, CU-UP, DU, and RU are used as examples in this application. Any one of the CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0064] In the embodiments of this application, the form of the network device is not limited. The device for implementing the functions of the network device can be the network device; it can also be a device that can support the network device to implement such functions, such as a chip system. This device can be installed in the network device or used in combination with the network device.

[0065] In the evolution process of communication systems, high throughput and large connections have always been the core challenges of wireless communication networks. To address the above challenges, 5G communication has proposed applications such as enhanced mobile broadband (eMBB), ultra reliable and low latency communication (URLLC), and massive machine type communication (mMTC) as technical goals. The 6G communication system evolved after 5G will surely evolve towards directions such as greater throughput, lower latency, higher reliability, larger connection numbers, and higher spectral efficiency.

[0066] Along with the continuous development of the three major driving forces of AI / ML, namely computing power, algorithms, and data-related technologies, AI / ML has important application potential in many aspects such as complex unknown environment modeling and learning, channel prediction, intelligent signal generation and processing, network state tracking and intelligent scheduling, and network optimization and deployment.

[0067] The implementation of AI technology may rely on the interaction between multiple devices. For large-scale AI models, when there are significant differences in computing power and storage capacity between devices, the training and inference of the AI model may be located on different devices. For example, compared to terminal devices, network devices with stronger computing and storage capabilities can be used for training the AI model. After the model training is completed, the network device can then distribute the AI model to the terminal device, and the terminal device uses the received AI model to perform the inference of the AI model. During the inference phase, when the collection of sample data is related to changes in the environment, when the external environment changes, the collected sample data also changes accordingly, which may result in the current sample data not matching the previously received AI model. At this time, the network device needs to send the updated AI model to the terminal device.

[0068] The training process of the AI model can also be completed through the cooperation of multiple devices. For example, in distributed learning, multiple terminal devices independently train the AI model using local sample data and send the weights or gradients of the model during the training process to the network device. The network device aggregates the received weights or gradients of multiple models and then distributes the aggregated results to multiple terminal devices. The above process is repeated iteratively until the model converges.

[0069] In addition, to ensure communication quality, access network devices also participate in the management of AI modules. In this application, an AI module is a module implemented through AI technology. For example, an access network device can obtain information related to the AI module, that is, identify the AI module, and configure the AI module according to the identification result. The AI module in the terminal device can perform data measurement and / or reporting based on the configuration of the access network device.

[0070] As Figure 2 shown, the AI modules currently deployed in terminal devices can be at the feature level, functionality level, and model level respectively. Among them, the functionality-level AI module is located below the feature-level AI module. A feature-level AI module can include multiple functionality-level AI modules, or it can be said that a feature-level AI module corresponds to one or more functionality-level AI modules; the model-level AI module is located below the functionality-level AI module. A functionality-level AI module can include multiple model-level AI modules. Among them, the model-level AI module contains an AI model. Therefore, Figure 2 a model in represents a model-level AI module or an AI model. It can also be said that the feature-level AI module supports one or more functionality-level AI modules, and a functionality-level AI module can support multiple model-level AI modules. In addition, Figure 2One feature therein represents a feature-level AI module, and one function represents a function-level AI module.

[0071] In the following text, the AI model, the model, and the model-level AI module can be considered equivalent descriptions and can be replaced with each other. Additionally, in the following text, the feature and the feature-level AI module can be considered equivalent descriptions and can be replaced with each other. Additionally, the function and the function-level AI module can be considered equivalent descriptions and can be replaced with each other.

[0072] In one example, the channel state information (CSI) prediction can be a function of a feature-level AI module. In different scenarios and configurations, this feature-level AI module can be further divided into multiple function-level AI modules. For example, the CSI prediction in a low-speed scenario and the CSI prediction in a high-speed scenario can be two independent function-level AI modules respectively, and these two independent function-level AI modules may be implemented based on different models. For instance, different models under different functions can have different inputs, outputs, structures, parameters, or additional conditions, etc.

[0073] Currently, in the case where the AI modules of the terminal device adopt a hierarchical configuration, how to efficiently configure the AI model by the access network device is a key problem to be urgently solved.

[0074] To solve the above technical problems, an embodiment of the present application provides a communication method. This communication method can be implemented by a first communication device and a second communication device. For example, the first communication device can be a terminal device or a chip or module in the terminal device, and the second communication device can be an access network device or a chip or module in the access network device.

[0075] Figure 3 It is a schematic flowchart of a data transmission method provided by an embodiment of the present application. The method includes the following steps:

[0076] S101: The access network device determines first information.

[0077] Among them, the first information includes a first identifier and first configuration information.

[0078] This first identifier can be used to identify or indicate a feature, a function, or a model.

[0079] This first configuration information can be used to configure all or part of the models associated with N1 features, all or part of the models associated with N2 functions, or N3 models. Among them, N1 features correspond to M1 functions, M1 functions correspond to M2 models, and M2 models are all or part of the models associated with N1 features. M1, M2, N1, N2, and N3 are all positive integers.

[0080] Among them, the N1 features may include the features identified by the first identifier, or the N2 functions may include the functions identified by the first identifier, or the N3 models may include the models identified by the first identifier.

[0081] Therefore, the first information can be used to configure at least one feature, at least one function, or at least one model.

[0082] S102: The access network device sends the first information. Correspondingly, the terminal device receives the first information.

[0083] Among them, the access network device may send the first information to the terminal device through the air interface between the access network device and the terminal device.

[0084] For example, the first information may be carried in a radio resource control (RRC) message, a media access control (MAC) control element (CE), or downlink control information (DCI) sent by the access network device to the terminal device.

[0085] S103: The terminal device applies the first configuration information to the first feature, the first function, or the first model according to the first identifier, where the first feature is at least one of the N1 features, the first function is at least one of the N2 functions, and the first model is at least one of the N3 models.

[0086] Among them, the first feature may include the features identified by the first identifier, or the first function may include the functions identified by the first identifier, or the first model may include the models identified by the first identifier. In this application, applying the configuration information to a feature, a function, or a model may mean that the configuration information is used to configure or set the feature, the function, or the model; that is to say, the configuration information is the configuration information of the feature, the function, or the model.

[0087] Based on Figure 3In the process shown, the access network device can indicate the configuration information of the AI model to the terminal device through the first information. Among them, the first information may include a first identifier and first configuration information. The first identifier can be used to indicate a feature, a function, or a model, that is, it can indicate that the first configuration information is at the feature, function, or model level. Correspondingly, the first configuration information is used to configure all or part of the models associated with N1 features, all or part of the models associated with N2 functions, or N3 models. That is to say, the first configuration information can be used to configure all or part of the models associated with the same feature, or the first configuration information can be applied to configure all or part of the models associated with the same function, or the first configuration information can be applied to configure one or more models, that is, it is not necessary to configure each model separately, which can improve the model configuration efficiency.

[0088] The first identifier and the first configuration information are described below respectively.

[0089] (1) The first identifier can be a feature identifier, a function identifier, or a model identifier. The feature identifier can be used to identify a feature, the function identifier can be used to identify a function, and the model identifier can be used to identify a model.

[0090] On the first hand, the first identifier can be used to represent the configuration level. For example, the first identifier may include level information, and the level information can be used to represent the feature level, the function level, or the model level. For example, the level information can be feature, functionality, or model, which are used to explicitly indicate features, functions, and models respectively. Another example is that the level information can also be other symbols or numbers associated with features, functions, and models respectively, which are used to implicitly indicate features, functions, and models. For example, the level information of the feature identifier can be 0, the level information of the function identifier can be 1, and the level information of the model identifier can be 2. The level information can also have other names, which are not specifically limited in this application.

[0091] On the second hand, the first identifier can distinguish different features, or be used to distinguish different functions, or be used to distinguish different models. For example, the first identifier includes an index, such as a number or a serial number.

[0092] Based on the first and second aspects, the first identifier can include two fields. Among them, the first field can be used to represent or indicate the level information. The second field can be used to represent or indicate the index of the feature, the index of the function, or the index of the model. Or, the first identifier can also include a field, which is used to indicate the level information and the index.

[0093] In one example, a feature identifier can be composed of a feature and a number. For example, feature 0 and feature 1 are used as different feature identifiers respectively, and feature can also be replaced by characteristic. Similarly, a functionality identifier can be composed of functionality and a number. For example, functionality 0 and functionality 1 are used as different functionality identifiers respectively, and functionality can also be replaced by function. Similarly, a model identifier can be composed of model and a number. For example, model 0 and model 1 are used as different model identifiers respectively, and model can also be replaced by model. In the above examples, feature, functionality, and model can be used as level information to indicate features, functionality, and models respectively.

[0094] In another example, the level information of a feature identifier can be 0, the level information of a functionality identifier can be 1, and the level information of a model identifier can be 2. For example, 00 represents a feature identifier, 10 represents a functionality identifier, and 20 represents a model identifier.

[0095] In another example, the level information can be associated with multiple numbers or serial numbers. For example, feature 012 represents three features numbered 0, 1, and 2.

[0096] In another example, the level information can be distinguished by different index ranges. For example, the index range 0 to 9 is 10 indexes at the feature level, the index range 10 to 19 is 10 indexes at the functionality level, and the index range 20 to 29 is 10 indexes at the model level. Among them, index 0 represents the first feature, index 12 represents the third functionality, and so on.

[0097] It can be understood that the feature identifier, functionality identifier, and model identifier can also be implemented in other ways other than the above examples, and the specific ways are not limited in this application.

[0098] (2) The first configuration information can be used as the configuration information of the model.

[0099] Among them, the first configuration information can be used to configure all or part of the models associated with N1 features, all or part of the models associated with N2 functionalities, or N3 models. Among them, N1 features correspond to M1 functionalities, M1 functionalities correspond to M2 models, and M2 models are all or part of the models associated with N1 features. M1, M2, N1, N2, and N3 are all positive integers.

[0100] It can also be described that the first configuration information can be used as feature-level configuration information to configure all or part of the models associated with N1 features. Alternatively, the first configuration information can be used as function-level configuration information to configure all or part of the models associated with N2 functions. The first configuration information can also be used as model-level configuration information to configure N3 models.

[0101] In various embodiments of the present application, the configuration information can be used for at least one of data measurement or data reporting. Or rather, the first configuration information can include at least one of data measurement parameters or data reporting parameters. The configuration information here can include the first configuration information, and can also include the second configuration information, the third configuration information, etc. mentioned below.

[0102] Among them, the data measurement parameters can include the parameters required for data measurement, and can be applied to the terminal device to collect the data required by the AI model. For example, the access network device can send a reference signal to the terminal device based on the data measurement parameters, and the terminal device can measure the reference signal based on the data measurement parameters, and the measurement result can be used as measurement data. The terminal device can also report the measurement result to the access network device according to the data reporting parameters to achieve data reporting. Among them, the measurement result can include a precoding matrix indicator (PMI), a reference signal receiving power (RSRP), a reference signal receiving quality (RSRQ), a channel quality indicator (CQI), a rank indication (RI), or a signal to interference plus noise ratio (SINR), etc.

[0103] For example, the data measurement parameter is, for example, a measurement object (MO). Among them, the measurement object may include one or more of the following parameters: the time-domain resource, frequency-domain resource of the reference signal to be measured, or the generation method of the sequence associated with the reference signal. Among them, the time-domain resource of the reference signal to be measured includes, for example, parameters such as the number of time slots occupied by the reference signal in the time domain, time slot index, number of symbols, symbol index, period, or offset within the period. The frequency-domain resource of the reference signal to be measured includes, for example, parameters such as the carrier, bandwidth part (BWP), resource block (RB), resource element (RE), frequency-domain interval, or frequency hopping method occupied by the reference signal in the frequency domain. The generation method of the sequence associated with the reference signal can be used to indicate or determine the sequence associated with the reference signal.

[0104] The data reporting parameter may include the data reporting parameter of the AI module. For example, the data reporting parameter is, for example, a reporting configuration (RC). Among them, the reporting configuration may include one or more of the following parameters: the time-domain resource or frequency-domain resource of the reporting information of the terminal device. The time-domain resource and / or frequency-domain resource can be used to carry the reporting information. The reporting information may include measurement data, and the measurement data is, for example, a measurement result. Among them, the time-domain resource of the reporting information includes, for example, parameters such as the number of time slots occupied in the time domain, time slot index, number of symbols, symbol index, period, or offset within the period. The frequency-domain resource of the reporting information includes, for example, parameters such as the carrier, BWP, RB, RE, frequency-domain interval, or frequency hopping method occupied by the reference signal in the frequency domain.

[0105] As an example, the first configuration information may be a measurement configuration, and the measurement configuration may include MO and / or RC. In a possible embodiment, the first configuration information may include a set of measurement configurations, and this set of measurement configurations can be used to configure multiple models of at least one function in the N1 feature. Or, this set of measurement configurations can be used to configure multiple models in the N2 function.

[0106] In this application, it can be considered that the measurement configuration is the specific content carried in the configuration information. In some cases, the measurement configuration and the configuration information can be replaced with each other.

[0107] For example, the access network device indicates one or more measurement configuration IDs and their associated measurement configurations through an RRC message, such as indicating a list containing the correspondence between the measurement configuration ID and the measurement configuration. At this time, the first configuration information may include the measurement configuration ID, and the terminal device may determine the measurement configuration associated with the measurement configuration ID from the list according to the measurement configuration ID. At this time, the first configuration information may be carried in the same or different RRC message, MAC CE, or DCI as the list.

[0108] As another example, the measurement target may correspond to a measurement target ID, and the reporting configuration may correspond to a reporting configuration ID. Therefore, the measurement target may be indicated by the measurement target ID, and / or the reporting configuration may be indicated by the reporting configuration ID. For example, the access network device indicates one or more measurement target IDs and their associated measurement targets and / or one or more reporting configuration IDs and their associated reporting configurations through an RRC message, such as indicating a list containing the correspondence between the measurement target ID and the measurement target and / or the correspondence between the reporting configuration ID and the reporting configuration. At this time, the first configuration information may include the measurement target ID and / or the reporting configuration ID, and the terminal device may determine the measurement target associated with the measurement target ID and / or the reporting configuration associated with the reporting configuration ID from the list according to the measurement target ID and / or the reporting configuration ID. At this time, the first configuration information may be carried in the same or different RRC message, MAC CE, or DCI as the list.

[0109] Optionally, the first configuration information may include a measurement identity (meas ID), and the measurement identity may indicate the measurement configuration. For example Figure 4 As shown, measurement identity 0 includes or corresponds to measurement target ID1 and reporting configuration ID1, that is, the measurement configuration associated with measurement identity 0 includes measurement target ID1 and reporting configuration ID1. In addition, measurement identity 1 corresponds to measurement target ID1 and reporting configuration ID2, and measurement identity 2 corresponds to measurement target ID2 and device configuration ID2. Based on Figure 4 it can be known that measurement identity 0 corresponds to feature 1, where feature 1 may include functions 0 to N-1, any function may include one or more models, and N is a positive integer greater than 1. That is to say, all or part of the models in functions 0 to N-1 included in feature 1 may adopt measurement target ID1 and reporting configuration ID1.

[0110] In addition, the first configuration information may include a measurement target ID and / or a reporting configuration ID. In this case, the first configuration information may not include a measurement identifier. For example, the terminal device obtains the measurement target ID and / or the reporting configuration ID according to the first configuration information, and determines the measurement target and / or the reporting configuration included in the measurement configuration according to the measurement target ID and / or the reporting configuration ID. Optionally, in order to reflect the association between the measurement target ID and the reporting configuration ID, in the first configuration information, the parameter associated with the measurement target ID may include the reporting configuration ID, or in other words, the reporting configuration ID may be used as one of the parameters of the measurement target associated with the measurement target ID. Or, the parameter associated with the reporting configuration ID may include the measurement target ID, or in other words, the measurement target ID may be used as one of the parameters of the reporting configuration associated with the reporting configuration ID.

[0111] Optionally, the above first identifier and the first configuration information may be carried in different fields of the first information. The first information may be an RRC message, a MAC CE, or a DCI.

[0112] In a possible embodiment, the first information may further include a second identifier, so that the first configuration information can also be used for the features, functions, or models indicated by the second identifier.

[0113] The second identifier may be used to identify a feature, a function, or a model.

[0114] The second identifier may refer to the description of the first identifier. The difference between the two is that the first identifier may be different from the second identifier. On the one hand, the first identifier and the second identifier may identify different levels of information. For example, the first identifier is used to identify a feature, and at this time, the second identifier may be used to identify a function or a model. On the other hand, in the case where the level of information is the same, the first identifier and the second identifier may have different numbers or serial numbers. For example, if the second identifier and the first identifier are both used to identify features, the number of the feature identified by the second identifier may be different from the number of the feature identified by the first identifier; or, if the second identifier and the first identifier are both used to identify functions, the number of the function identified by the second identifier may be different from the number of the function identified by the first identifier; or, if the second identifier and the first identifier are both used to identify models, the number of the model identified by the second identifier may be different from the number of the model identified by the first identifier.

[0115] In this embodiment, the terminal device may apply the first configuration information to the second feature, the second function, or the second model. The second feature may include the feature identified by the second identifier, or the second function may include the function identified by the second identifier, or the second model may include the model identified by the second identifier.

[0116] As an example, the second feature is at least one of the N1 features shown in S103, the second function is at least one of the N2 functions shown in S103, and the second model is at least one of the N3 models shown in S103.

[0117] As Figure 4 shown, the first information may include Function 0 and Function 1, and include Measurement ID 2. The measurement configuration associated with Measurement ID 2 can be used for Function 0 and Function 1. Among them, Function 0 and Function 1 serve as the first identifier and the second identifier respectively, and the measurement configuration associated with Measurement ID 2 can serve as the first configuration information.

[0118] Based on this embodiment, the first information may include multiple identifiers, such as the first identifier and the second identifier. The multiple identifiers may correspond to different features, functions, or models. At this time, the first configuration information can be used to configure the features, functions, or models indicated by the multiple identifiers respectively. Among them, the multiple identifiers may include the first identifier and the second identifier. Therefore, the first configuration information can be configured for the different features, functions, or models indicated by the multiple identifiers to achieve efficient configuration of the model. The first information may also include more identifiers other than the first identifier and the second identifier, and the first configuration information can be applicable to the features, functions, or models indicated by the multiple identifiers. This application does not specifically limit.

[0119] In a possible embodiment, the first information may further include a second identifier and second configuration information, such that the first configuration information is applied to the feature, function, or model indicated by the first identifier, and the second configuration information is applied to the feature, function, or model indicated by the second identifier.

[0120] Among them, the second identifier can be used to identify a feature, a function, or a model. The second identifier can follow the description in the previous embodiment.

[0121] The second configuration information can refer to the description of the first configuration information. Among them, the second configuration information is used to configure all or part of the models associated with L1 features, all or part of the models associated with L2 functions, or L3 models. The second configuration information can be the same as or different from the first configuration information. The L1 features can correspond to K1 functions, the K1 functions can correspond to K2 models, and the K2 models are all or part of the models associated with the L1 features. K1, K2, L1, L2, and L3 are all positive integers.

[0122] In this embodiment, the terminal device can apply the second configuration information to the second feature, the second function, or the second model. Among them, the second feature may include the feature identified by the second identifier, or the second function may include the function identified by the second identifier, or the second model may include the model identified by the second identifier.

[0123] As an example, the second feature is at least one of L1 features, the second function is at least one of L2 functions, and the second model is at least one of L3 models.

[0124] As Figure 4 shown, the first information may include feature 1, measurement identifier 0 associated with feature 1, function 1, and measurement identifier 1 associated with function 1. Among them, feature 1 can be used as the first identifier, and correspondingly, the measurement configuration associated with measurement identifier 0 can be used as the first configuration information. In addition, Figure 4 function 1 in

[0125] Based on this embodiment, the first information may include multiple identifiers and multiple configuration information. The multiple identifiers may correspond to different features, functions, or models; the multiple configuration information may respectively configure the features, functions, or models indicated by different identifiers to achieve efficient configuration of the AI model. For example, the multiple identifiers include a first identifier and a second identifier, and the multiple configuration information includes a first configuration information and a second configuration information. The first configuration information can be used for the features, functions, or models identified by the first identifier, and the second configuration information can be used for the features, functions, or models identified by the second identifier. The first information may also include more identifiers other than the first identifier and the second identifier, and more configuration information other than the first configuration information and the second configuration information. This more configuration information can be used for the features, functions, or models identified by more identifiers, and the present application does not specifically limit.

[0126] In a possible embodiment, the first information may further include a third configuration information, such that the first configuration information and the third configuration information are respectively used for some models in the features indicated by the first identifier, or such that the first configuration information and the third configuration information are respectively used for some models in the functions identified by the first identifier.

[0127] Among them, the third configuration information may refer to the description of the first configuration information.

[0128] In this embodiment, the terminal device may configure the first configuration information to the first part of the models associated with N1 features, and the third configuration information may be configured to the second part of the models associated with N1 features. Among them, the first part of the models is different from the second part of the models. For example, the first part of the models and the second part of the models are respectively a part of the multiple models associated with the first feature. For example, the models associated with the first feature include model 1 and model 2. The terminal device may configure the first configuration information to model 1 and configure the third configuration information to model 2.

[0129] As Figure 5As shown, the first information may include Feature 1, Measurement ID 0, and Measurement ID 1. The models associated with Feature 1 include Model 0 to Model 4. Among them, Feature 1 can be used as the first identifier. Correspondingly, the measurement configuration associated with Measurement ID 0 can be used as the first configuration information, and the measurement configuration associated with Measurement ID 1 can be used as the third configuration information. The terminal device can use the measurement configuration associated with Measurement ID 0 for Model 0 and Model 1 associated with Feature 1. In addition, the terminal device can use the measurement configuration associated with Measurement ID 0 for Model 3 and Model 4 associated with Feature 1. Among them, Model 0 and Model 1 can be used as the first part of the models associated with Feature 1, and Model 3 and Model 4 can be used as the second part of the models associated with Feature 1.

[0130] Based on this embodiment, the first information can include an identifier and multiple configuration information. The identifier can be used to identify a feature or a function. Among them, the number of models associated with the feature or function is multiple. At this time, multiple configuration information can be used to configure different models respectively to achieve efficient configuration of AI models.

[0131] Next, the method for the access network device to determine the level of configuration information will be described. The level of configuration information can refer to that the configuration information is applied to all or part of the models in the feature, or all or part of the models in the function, or applied to one or more models.

[0132] Method 1: The access network device can determine the level of configuration information based on the recognition result of model recognition.

[0133] Among them, model recognition can refer to that the terminal device provides its own model information to the access network device. The model information includes, for example, at least one of the feature identifier of the terminal device's feature, the function identifier of the function, and the model identifier of the model, so that the access network device can recognize which features, functions, or models the terminal device has, in order to configure the terminal device's features, functions, or models, and improve the configuration efficiency.

[0134] Optionally, the terminal device can send its own model information to the access network device at a certain period, or after the first access to the access network device, or when the terminal device starts to enable its own model.

[0135] Among them, if the access network device cannot recognize the model of the terminal device, that is, it can only recognize the features and / or functions of the terminal device, the access network device can configure the configuration information at the feature level or the function level for the terminal device.

[0136] For example, if the access network device identifies the characteristics of the terminal device but cannot identify what functions and models the terminal device has, the access network device can provide feature-level configuration for the terminal device. For example, the access network device can send the first information to the terminal device, and the first information can include a first identifier and first configuration information. The first identifier can be used to indicate a feature, and the first configuration information can be used for the configuration of the models in the feature. That is to say, the terminal device can apply the first configuration information to one or more models in the feature.

[0137] For another example, if the access network device identifies the functions of the terminal device but cannot identify what models the terminal device has, the access network device can provide function-level configuration for the terminal device. For example, the access network device can send the first information to the terminal device, and the first information can include a first identifier and first configuration information. The first identifier can be used to indicate a function, and the first configuration information can be used for the configuration of the models in the function. That is to say, the terminal device can apply the first configuration information to one or more models in the function.

[0138] That is to say, in the case where the access network device cannot identify the models in the terminal device, the multiple models in each feature of the terminal device can correspond to the same configuration information, or the multiple models in each function of the terminal device can correspond to the same configuration information.

[0139] If the access network device can identify the models in the terminal device, it can provide model-level configuration for the terminal device, that is, provide configuration for one or more models. For example, if the access network device identifies that the terminal device has Model 1 and Model 2, the access network device can provide model-level configuration for Model 1 and Model 2 respectively. For example, the access network device can send the first information to the terminal device, and the first information can include a first identifier, a second identifier, and first configuration information. The first identifier can be used to indicate Model 1, the second identifier can be used to indicate Model 2, and the first configuration information can be used for the configuration of Model 1 and Model 2. That is to say, the terminal device can apply the first configuration information to Model 1 and Model 2. That is to say, in the case where the access network device can identify the models in the terminal device, each model of the terminal device can correspond to a set of independent configuration information.

[0140] In Way 2, the access network device can determine the level of the configuration information based on the request of the terminal device, or rather, the terminal device can explicitly indicate the required configuration level.

[0141] In Way 2, the terminal device can send a first request to the access network device, and the first request can be used to request the configuration of N1 features, N2 functions, or N3 models.

[0142] The first request may include level information for indicating the configuration level requested by the terminal device. For example, the level information can be used to indicate features, functions, or models. Correspondingly, the access network device may provide configuration information at the corresponding level according to the level information requested by the terminal device. For example, the access network device may provide at least one piece of configuration information, and indicate through an identifier associated with the configuration information the level to which the configuration information applies, which is a feature, a function, or a model. For example, the identifier here may be a first identifier, a second identifier, or a third identifier, and the configuration information may be a first piece of configuration information, a second piece of configuration information, or a third piece of configuration information.

[0143] In addition, the first request can also be used to request to provide P1 configurations for N1 features, P2 configurations for N2 functions, or P3 configurations for the N3 models, that is, the first request may carry the quantity information of P1, P2, or P3. Among them, P1, P2, or P3 can be positive integers.

[0144] As an example, when the terminal device requests multiple feature-level configurations, the access network device can provide multiple feature-level configurations according to the request of the terminal device. The terminal device can use one feature-level configuration for the first part of the models in one feature, and use other feature-level configurations for the second part of the models in the same feature. Similarly, when the terminal device requests multiple function-level configurations, the access network device can provide multiple function-level configurations according to the request of the terminal device. The terminal device can use one function-level configuration for the first part of the models in one feature, and use other function-level configurations for the second part of the models in the same feature. The advantage of this is that in some cases, multiple measurement configurations can be adopted for multiple models associated with the same feature or function. For example, when the structures of multiple models associated with the same feature or function are similar, the multiple models can adopt the same measurement configuration.

[0145] Taking the function-level configuration as an example, the access network device does not recognize the model of the terminal device, but only recognizes the function of the terminal device. At this time, the terminal device can request the access network device to provide multiple sets of measurement configurations for a certain function. After receiving multiple sets of measurement configurations, the terminal device can determine the association between the models and the multiple measurement configurations by itself. Among them, the number of measurement configurations is multiple, and the multiple measurement configurations all correspond to the same function. The access network device does not need to specify the association between the measurement configuration and the model, and the terminal device itself decides which models adopt which measurement configuration. Optionally, at this time, the terminal device can indicate to the access network device through the first request that multiple configurations need to be provided for the same function, that is, P2 is greater than 1. The terminal device can also indicate the reason, such as the structures of multiple models associated with the same function are similar, so the access network device can know to provide the same measurement configuration for the models with similar structures.

[0146] Such as Figure 5As shown, the terminal device may request the access network device to allocate two sets of measurement configurations for Function 1, and the access network device may provide two sets of measurement configurations associated with Measurement Configuration ID0 and Measurement Configuration ID1 respectively. The terminal device itself determines that Measurement Configuration ID 0 corresponds to Model 0 and Model 1, and determines that Measurement Configuration ID1 corresponds to Model 2 and Model 3 corresponding to the second set of measurement configurations.

[0147] In various embodiments of the present application, multiple configuration information provided by the access network device may share a measurement target or a reporting configuration. Among them, the multiple configuration information includes at least one of the foregoing first configuration information, second configuration information, or third configuration information. For example Figure 4 As shown, the measurement configurations associated with Measurement ID 0 and Measurement ID 1 respectively may have the same measurement target, that is, the measurement target with ID 1. Another example is that the measurement configurations associated with Measurement ID 2 and Measurement ID 3 respectively may have the same reporting configuration, that is, the reporting configuration with ID 2.

[0148] Among them, the specific parameters of the shared measurement target and reporting configuration do not need to be repeatedly carried to reduce channel overhead.

[0149] In the present application, the terminal device may indicate to the access network device the sharing method of the requested measurement configuration. Among them, the terminal device may indicate to the access network device to request sharing of the measurement target or sharing of the reporting configuration. For example, the terminal device may inform the access network device of the request to share. Another example is that taking the sharing of the measurement target as an example, the terminal device may indicate to the access network device to share multiple measurement identifiers of the same measurement target, or the terminal device may indicate to the access network device the number of multiple measurement configurations sharing the same measurement target. Accordingly, the access network device may provide the corresponding shared measurement configuration to the terminal device according to the request of the terminal device. In addition, the access network device may also decide according to its own configuration to share multiple measurement configurations of the same measurement target or reporting configuration.

[0150] In a possible embodiment, any configuration information in the present application may correspond to one of multiple stages. In the present application, the multiple stages may include a training stage, an inference stage, or a monitoring stage, that is, any configuration information may correspond to the training stage, the inference stage, or the monitoring stage. Among them, the configuration information corresponding to the training stage can be used for the model in the training stage; the configuration information corresponding to the inference stage can be used for the model in the inference stage; the configuration information corresponding to the monitoring stage can be used for the model in the monitoring stage.

[0151] For example, the first configuration information can be used for all or part of the models associated with N1 features in the first stage, all or part of the models associated with N2 functions in the first stage, or N3 models in the first stage. The first stage is one of the training stage, the inference stage, or the monitoring stage.

[0152] Among them, in the training stage, the model needs to collect the input data and output data of the model and train the model; in the inference stage, the model needs to collect the input of the model for inference; in the monitoring stage, the model needs to collect the actual output of the model and relevant auxiliary information for model monitoring. Therefore, the same model can adopt different measurement configurations in different stages to meet the requirements for data collection and / or reporting in different stages.

[0153] Specifically, in the training stage, the data that the model needs to collect includes the input data and the ground truth of the model. Therefore, the measurement configuration in the training stage can be used for the measurement and / or reporting of the input data and / or the ground truth.

[0154] In the inference stage, the data that the model needs to collect includes the input data of the model. Therefore, the measurement configuration in the inference stage can be used for the measurement and / or reporting of the input data.

[0155] In the monitoring stage, the data that the model needs to collect includes the ground truth of the model. Therefore, the measurement configuration in the inference stage can be used for the measurement and / or reporting of the ground truth.

[0156] In this embodiment, the configuration information can carry stage information, and the stage information can be used to indicate or identify the stage associated with the configuration information, and this stage can be called the first stage. The first stage can be the training stage, the inference stage, or the monitoring stage. The configuration information here includes but is not limited to the first configuration information, the second configuration information, or the third configuration information in this application. The stage information can also have other names, which are not specifically limited in this application.

[0157] For example, when the value of the stage information is the first value, it can indicate the training stage; when the value of the stage information is the second value, it can indicate the inference stage; when the value of the stage information is the third value, it can indicate the monitoring stage. As an example, the first value is 0, the second value is 1, and the third value is 2. As another example, the first value, the second value, and the third value are respectively the names of the training stage, the inference stage, and the monitoring stage. For example, the first value is training or training stage, the second value is inference or inference stage, and the third value is monitoring or monitoring stage. In addition, the first value, the second value, and the third value of the above level information can also be set to other values, which are not specifically limited in this application.

[0158] It can be understood that the access network device can configure different measurement configurations for the same feature, function, or model at different stages.

[0159] In combination with the level information, if the level information indicates a feature and the stage information indicates the first stage, the terminal can apply the configuration information to the models in the first stage of some or all of the models in the feature. In the case where the above models are in other stages other than the first stage, the configuration information may not be adopted. If the level information indicates a function and the stage information indicates the first stage, the terminal can apply the configuration information to the models in the first stage of some or all of the models in the function. In the case where the above models are in other stages other than the first stage, the configuration information may not be adopted. If the level information indicates a model and the stage information indicates the first stage, the terminal can apply the configuration information to the model in the first stage. In the case where the model is in other stages other than the first stage, the configuration information may not be adopted.

[0160] Optionally, different training stages can share measurement targets, or in other words, models in different training stages can adopt the same measurement targets. Additionally, different training stages can share reporting configurations, or in other words, models in different training stages can adopt the same reporting configurations.

[0161] Such as Figure 6 shown, as an example, measurement identifier 0 corresponds to feature 1 in the training stage, measurement identifier 1 corresponds to feature 1 in the monitoring stage, and measurement identifier 2 corresponds to feature 1 in the inference stage. Among them, measurement identifier 0 and measurement identifier 1 can adopt the same measurement target. Measurement identifier 1 and measurement identifier 2 can adopt the same reporting configuration.

[0162] In addition, it is not excluded that different training stages share a measurement configuration, that is, share measurement targets and reporting configurations. For example, the training stage and the inference stage can share measurement targets and reporting configurations.

[0163] Taking the multiple stages as the training stage and the inference stage as an example, Figure 7 shown is the situation where models in different stages share a measurement configuration when the training stage and the inference stage are allowed to share a measurement configuration: both the measurement target and the reporting configuration of the measurement configuration associated with measurement identifier 0 can be shared by the training stage and the inference stage. Measurement identifier 1 and measurement identifier 2 share the measurement target with ID 1, where measurement identifier 1 and measurement identifier 2 can respectively correspond to the training stage and the inference stage. Measurement identifier 3 and measurement identifier 4 share the reporting configuration with ID 3, where measurement identifier 3 and measurement identifier 4 can respectively correspond to the training stage and the inference stage.

[0164] In this embodiment, the access network device may indicate, through signaling, that each stage corresponds to a set of measurement configurations, or multiple stages may share a set of measurement configurations. For example, the access network device indicates to the terminal device, through an RRC message, a MAC CE, or DCI, that each stage corresponds to a set of measurement configurations, or multiple stages may share a set of measurement configurations. Each stage corresponding to a set of measurement configurations may also be replaced with: different measurement configurations are used for different stages.

[0165] In this application, if each stage corresponds to a set of measurement configurations, the access network device may separately allocate measurement configurations for different stages of the same feature, function, or model. For example, the training stage, inference stage, and monitoring stage of the same feature respectively correspond to different measurement identifiers. Here, the feature may also be replaced with a function or a model. If multiple stages may share a set of measurement configurations, the access network device may provide the same measurement configuration for different stages of multiple different features, functions, or models. For example, at least two of the training stage, inference stage, or monitoring stage respectively correspond to the same measurement identifier, so as to reduce the signaling overhead and configurable complexity in the configuration process.

[0166] In one implementation manner of this embodiment, the terminal device may request the access network device to provide the same measurement configuration for features of at least two different stages. Here, the feature may also be replaced with a function or a model. Accordingly, the access network device may associate the same configuration information with different stage information. For example, the training stage and the inference stage may share one configuration information. The manner of associating the configuration information with different stage information is, for example, the stage information of multiple stages is carried in the configuration information, or the configuration information and the stage information of multiple stages are carried in different fields of the first information, etc., which is not specifically limited in this application.

[0167] In another implementation manner of this embodiment, the terminal device may also request a measurement configuration for any one of the training stage, inference stage, or monitoring stage. Accordingly, the configuration information provided by the access network device may be for one stage.

[0168] Among them, the terminal device may request the access network device to provide measurement configurations for features of different stages respectively. Here, the feature may also be replaced with a function or a model. Accordingly, the access network device may separately provide configuration information for different stages to provide measurement configurations. For example, the access network device may separately configure different measurement configurations for the training stage and the inference stage of the same feature, function, or model. Optionally, different measurement configurations may share the same measurement target or reporting configuration.

[0169] For example, the terminal device requests the access network device to provide a measurement configuration for the training phase, the inference phase, and the monitoring phase respectively. At this time, the access network device can provide three configuration information to the terminal device, and these three configuration information respectively correspond to the training phase, the inference phase, and the supervision phase. In this example, the measurement configurations for the training phase, the inference phase, and the monitoring phase can be completely independent, that is, these three measurement configurations correspond to different measurement identifiers.

[0170] Optionally, the terminal device can request a measurement configuration from the access network device through a first request. Among them, the second information can be carried in the first request, and the second information can be used to request the provision of the same or different configuration information for multiple phases. For example, the second information can indicate whether to provide the same or different configuration information for multiple phases through 1 bit. Among them, a value of 0 can indicate a request to provide the same configuration information for multiple phases, and a value of 1 indicates a request to provide different configuration information for multiple phases. Another example is that the value of the second information can be set to "shared" or "non-shared", where "shared" can indicate a request to provide the same configuration information for multiple phases, and "non-shared" can indicate a request to provide different configuration information for multiple phases.

[0171] In addition, the first request can also carry the phase information of each of the multiple phases. Among them, the phase information combined with the second information can be used to indicate the multiple different phases for which the terminal device requests to share the same configuration information, or to indicate the different phases for which the terminal device requests to use different configuration information.

[0172] Take Figure 7 as an example. If the second information is combined with the phase information and is used to request to provide the same measurement target and reporting configuration for the models in the training phase and the inference phase, the access network device can provide the measurement configuration associated with the measurement identifier 0 shown in Figure 7 ; if the second information is combined with the phase information and requests to provide the same measurement target for the models in the training phase and the inference phase, the access network device can provide the measurement configurations associated with the measurement identifier 1 and the measurement identifier 2 shown in Figure 7 . These two measurement configurations are respectively used for the model (or function or feature) in the training phase and the model (or function or feature) in the inference phase; if the second information is combined with the phase information and requests to provide the same reporting configuration for the models in the training phase and the inference phase, the access network device can provide the measurement configurations associated with the measurement identifier 3 and the measurement identifier 4 shown in Figure 7 . These two measurement configurations are respectively used for the model (or function or feature) in the training phase and the model (or function or feature) in the inference phase.

[0173] It can be understood that the combination of the above second information and the stage information can also be used as an independent piece of information, such as the third information. That is to say, the third information can be carried in the first request, and the third information can be used to indicate multiple stages and whether the multiple stages share the same measurement configuration. For example, the third information can be the information obtained by combining the second information and the stage information. For example, the field where the third information is located includes 1 bit and the stage information of at least two stages. This 1 bit can be used to indicate whether the multiple stages share the configuration information, and the stage information can be used to indicate the multiple stages.

[0174] Further optionally, the training stage may include different types such as initial training, fine-tuning, and updating. Among them, the same model can adopt different measurement configurations in different types of training stages, and its implementation method can refer to the implementation method of the model adopting different measurement configurations in different stages, which will not be elaborated here.

[0175] In a possible embodiment, any configuration information in this application can correspond to one of multiple requirements. In this application, the requirements can represent requirements in aspects such as the accuracy level of the model or the length of the training duration. Taking accuracy as an example, the accuracy of the model can include high accuracy, low accuracy, or medium accuracy, that is, any configuration information can correspond to high accuracy, low accuracy, or medium accuracy. Among them, the configuration information corresponding to high accuracy can be used for a high-accuracy model; the configuration information corresponding to low accuracy can be used for a low-accuracy model; the configuration information corresponding to medium accuracy can be used for a medium-accuracy model.

[0176] In addition, the accuracy is also classified according to different levels, that is, there are at least two different accuracy levels in total. For example, the accuracy level is divided into 0-5, indicating a total of 6 different levels. Different levels can correspond to different measurement configurations.

[0177] There can also be other classification methods for accuracy, which are not specifically limited in this application. For the convenience of description below, an example is given where the accuracy includes high accuracy, low accuracy, or medium accuracy, and other implementation methods of accuracy can be referred to for implementation.

[0178] For example, the first configuration information can be used for all or part of the models associated with N1 features of the first requirement, all or part of the models associated with N2 functions of the first requirement, or N3 models of the first requirement. Among them, taking the accuracy requirement as an example, the first requirement is one of high accuracy, low accuracy, or medium accuracy.

[0179] Among them, the measurement targets required by high-precision models have a higher resource frequency density, a smaller time-domain period, and a finer measurement granularity. For example, high-precision models require access network devices to provide measurement configurations at the resource element (RE) level. Additionally, the reporting configurations required by high-precision models need to support the reporting of a larger variety and quantity of measurement results. Compared with the measurement targets of high-precision models, the measurement targets of low-precision models have a lower resource frequency density, a longer time-domain period, and a coarser measurement granularity. For example, access network devices are required to provide measurements at the RB or sub-band level. Additionally, the reporting configurations of low-precision models only need to support the reporting of a smaller variety and quantity of measurement results. The requirements of medium-precision models for measurement targets and device configurations fall between those of high-precision models and low-precision models.

[0180] In this embodiment, the configuration information may carry precision information, which can be used to indicate or identify the precision associated with the configuration information. This precision can be referred to as the first requirement. The first requirement can be high precision, low precision, or medium precision. The configuration information here includes, but is not limited to, the first configuration information, the second configuration information, or the third configuration information in this application. The precision information may also have other names, which are not specifically limited in this application.

[0181] For example, when the value of the precision information is the first value, it can indicate high precision; when the value of the precision information is the second value, it can indicate low precision; when the value of the precision information is the third value, it can indicate medium precision. As an example, the first value is 0, the second value is 1, and the third value is 2. As another example, the first value, the second value, and the third value are respectively the names of high precision, low precision, and medium precision. For instance, the first value is high or high accuracy, the second value is low or low accuracy, and the third value is medium or medium accuracy. Additionally, the first value, the second value, and the third value of the above precision information can also be set to other values, which are not specifically limited in this application.

[0182] In this application, the precision information can be reported by the terminal device to the access network device. For example, during the model identification phase, the terminal device can report identification information related to at least one of its own characteristics, functions, or models to the access network device. Among them, the identification information reported by the terminal device may include the precision information of at least one of the characteristics, functions, or models. Also, for example, the identification information reported by the terminal device may include information such as the performance or quality of service (QoS) of at least one of the characteristics, functions, or models. Correspondingly, the access network device can determine the precision information of the model based on the model performance or quality of service.

[0183] The manner in which the access network device determines the accuracy information based on information such as performance or quality of service does not fall within the scope defined by this application. As an example, QoS may include accuracy requirements and latency requirements, where the accuracy requirements may indicate the accuracy information required by the terminal device.

[0184] It can be understood that the access network device can configure different measurement configurations for the same feature, function, or model at different accuracies.

[0185] In combination with the level information, if the level information indicates a feature and the accuracy information indicates a first requirement, the terminal can apply the configuration information to the models with the first requirement in some or all of the models in this feature. When the above models are at other accuracies outside the first requirement, the configuration information may not be adopted. If the level information indicates a function and the accuracy information indicates a first requirement, the terminal can apply the configuration information to the models with the first requirement in some or all of the models in this function. When the above models are at other accuracies outside the first requirement, the configuration information may not be adopted. If the level information indicates a model and the accuracy information indicates a first requirement, the terminal can apply the configuration information to this model with the first requirement. When this model is at other accuracies outside the first requirement, the configuration information may not be adopted.

[0186] Optionally, different accuracies can share the measurement target, or in other words, models with different accuracies can adopt the same measurement target. Additionally, different accuracies can share the reporting configuration, or in other words, models with different accuracies can adopt the same reporting configuration. Furthermore, it is not excluded that different accuracies share a measurement configuration, that is, they share the measurement target and the reporting configuration. For example, a high-accuracy model and a medium-accuracy model share the measurement target and the reporting configuration.

[0187] Optionally, in this embodiment, the access network device can indicate through signaling that each accuracy corresponds to a set of measurement configurations or multiple accuracies can share a set of measurement configurations. For example, the access network device indicates to the terminal device through an RRC message, a MAC CE, or a DCI that each accuracy corresponds to a set of measurement configurations or multiple accuracies can share a set of measurement configurations. Each accuracy corresponding to a set of measurement configurations can also be replaced with: different accuracies adopt different measurement configurations.

[0188] In this application, if each precision corresponds to a set of measurement configurations, the access network device can allocate measurement configurations for different precisions of the same feature, function, or model respectively. For example, the same feature corresponds to different measurement identifiers under high precision, low precision, or medium precision. Here, the feature can also be replaced by a function or a model. If multiple precisions can share a set of measurement configurations, the access network device can provide the same measurement configuration for different precisions of multiple different features, functions, or models. For example, at least two of high precision, low precision, or medium precision can correspond to the same measurement identifier to reduce the signaling overhead and configurable complexity during the configuration process.

[0189] In one implementation of this embodiment, the terminal device can request the access network device to provide the same measurement configuration for at least two features with different precisions. Here, the feature can also be replaced by a function or a model. Correspondingly, the access network device can associate the same configuration information with different precision information. For example, high precision and medium precision can share one configuration information. The way of associating the configuration information with different precision information is, for example, the configuration information carries the precision information of multiple precisions respectively, or the configuration information and the precision information of multiple precisions are carried in different fields of the first information, etc. This application does not specifically limit. Here, the precision information can be replaced by information such as performance or quality of service for determining the precision information.

[0190] In another implementation of this embodiment, the terminal device can also request a measurement configuration for any one of high precision, low precision, or medium precision. Correspondingly, the configuration information provided by the access network device can be for one precision.

[0191] The terminal device can request the access network device to provide measurement configurations for features with different precisions respectively. Here, the feature can also be replaced by a function or a model. Correspondingly, the access network device can provide the configuration information of the feature for different precisions respectively to provide the measurement configuration. For example, the access network device can configure different measurement configurations for high precision and medium precision of the same feature. Optionally, different measurement configurations can share the same measurement target or reporting configuration.

[0192] For example, the terminal device requests the access network device to provide a measurement configuration for high precision, low precision, and medium precision respectively. At this time, the access network device can provide three configuration information to the terminal device, and these three configuration information correspond to high precision, low precision, and medium precision respectively. In this example, the measurement configurations of high precision, low precision, and medium precision can be completely independent, that is, these three measurement configurations correspond to different measurement identifiers.

[0193] Optionally, the terminal device may request a measurement configuration from the access network device through a first request. The first request may carry fourth information, which can be used to request the same or different configuration information for multiple precisions. For example, the fourth information may indicate whether to provide the same or different configuration information for multiple precisions through 1 bit. A value of 0 may indicate a request to provide the same configuration information for multiple precisions, and a value of 1 indicates a request to provide different configuration information for multiple precisions. For another example, the value of the fourth information may be set to "shared" or "non-shared", where "shared" may indicate a request to provide the same configuration information for multiple precisions, and "non-shared" may indicate a request to provide different configuration information for multiple precisions.

[0194] In addition, the first request may also carry the precision information of each of the multiple precisions. The stage information, combined with the fourth information, can be used to indicate that the terminal device requests multiple different precisions that share the same configuration information, or to indicate that the terminal device requests different precisions with different configuration information.

[0195] It can be understood that the combination of the above fourth information and precision information can also be used as an independent piece of information, such as fifth information. That is, the first request may carry the fifth information, which can be used to indicate multiple precisions and whether the multiple precisions share the same measurement configuration. For example, the fifth information may be information obtained by combining the fourth information and the precision information. For example, the field where the fifth information is located includes 1 bit and the precision information of at least two precisions. The 1 bit can be used to indicate whether the multiple precisions share the configuration information, and the precision information can be used to indicate the multiple precisions.

[0196] It can be understood that in order to implement the functions in the above embodiments, the embodiments of the present application also provide a communication device. The communication device may include a corresponding hardware structure and / or software module that executes each function of the above terminal device and / or access network device. Those skilled in the art should easily realize that, in combination with the units and method steps of the examples described in the embodiments disclosed in the present application, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the form of hardware or computer software driving hardware depends on the specific application scenario and design constraints of the technical solution.

[0197] Figure 8 The structural schematic diagram of a communication device provided by the embodiments of the present application is given. The communication device 800 may be Figure 3 the terminal device shown or the circuit system in the terminal device, used to implement the method corresponding to the terminal device in the above method embodiments. Alternatively, the communication device 800 may be Figure 3The access network device or the circuit system of the access network device described in the illustrated embodiment is used to implement the method corresponding to the access network device in the above method embodiment. Among them, for example, a circuit system is a chip system.

[0198] The communication device 800 includes at least one processor 801. The processor 801 can be used for internal processing of the device to implement certain control and processing functions. Optionally, the processor 801 includes instructions. Optionally, the processor 801 can store data. Optionally, different processors can be independent devices, can be located in different physical locations, and can be located on different integrated circuits. Optionally, different processors can be integrated in one or more processors, for example, integrated on one or more integrated circuits.

[0199] Optionally, the communication device 800 includes one or more memories 803 for storing instructions. Optionally, data can also be stored in the memory 803. The processor and the memory can be set separately or integrated together.

[0200] Optionally, the communication device 800 includes a communication line 802 and at least one communication interface 804. Among them, since the memory 803, the communication line 802, and the communication interface 804 are all optional, they are Figure 8 all represented by dashed lines.

[0201] Optionally, the communication device 800 may further include a transceiver and / or an antenna. Among them, the transceiver can be used to send information to other devices or receive information from other devices. The transceiver can be referred to as a transceiver, a transceiver circuit, an input / output interface, etc., and is used to implement the transceiver function of the communication device 800 through the antenna. Optionally, the transceiver includes a transmitter and a receiver. Exemplarily, the transmitter can be used to generate a radio frequency signal from a baseband signal, and the receiver can be used to convert a radio frequency signal into a baseband signal.

[0202] The processor 801 may include a general-purpose central processing unit (CPU), a microprocessor, an application specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present application solution.

[0203] The communication line 802 may include a path for transmitting information between the above components.

[0204] A communication interface 804, using any transceiver-like device, is used to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), wired access network, etc.

[0205] The memory 803 can be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or it can also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but not limited to this. The memory 803 can exist independently and be connected to the processor 801 through the communication line 802. Alternatively, the memory 803 can also be integrated with the processor 801.

[0206] Among them, the memory 803 is used to store computer execution instructions for implementing the solution of this application, and is controlled by the processor 801 for execution. The processor 801 is used to execute the computer execution instructions stored in the memory 803, so as to implement Figure 3 the steps performed by the UE or network device described in the illustrated embodiments.

[0207] Optionally, the computer execution instructions in the embodiments of this application can also be referred to as application code, and this application does not make specific limitations on this.

[0208] In a specific implementation, as an embodiment, the processor 801 can include one or more CPUs, such as Figure 8 CPU0 and CPU1 in

[0209] In a specific implementation, as an embodiment, the communication device 800 can include multiple processors, such as Figure 8The processors 801 and 805 therein. Each of these processors can be a single-CPU processor or a multi-CPU processor. The processors here can refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0210] When Figure 8 The device shown is a chip, such as a chip of a UE or a chip of a network device, then the chip includes a processor 801 (and may also include a processor 805), a communication line 802, and a communication interface 804. Optionally, it may include a memory 803. Specifically, the communication interface 804 can be an input interface, a pin, a circuit, etc. The memory 803 can be a register, a cache, etc. The processors 801 and 805 can be a general-purpose CPU, a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of a program for any of the above-described communication methods.

[0211] Embodiments of the present application can perform functional module partitioning on the device according to the above method examples. For example, each functional module can be partitioned corresponding to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of a software functional module. It should be noted that the partitioning of modules in the embodiments of the present application is illustrative, only a logical function partitioning, and there can be other partitioning methods in actual implementation. For example, in the case of partitioning each functional module corresponding to each function, Figure 9 A schematic diagram of a device is shown. The device 900 can include the UE or the network device involved in each of the above method embodiments, or include a chip in the UE or a chip in the network device. The device 900 includes a sending unit 901, a processing unit 902, and a receiving unit 903.

[0212] It should be understood that the device 900 can be used to implement the steps performed by the UE or the network device in the communication method of the embodiments of the present application, and the relevant features can be referred to the above Figure 3 shown embodiments and will not be elaborated here.

[0213] Optionally, Figure 9 the functions / implementation processes of the sending unit 901, the receiving unit 903, and the processing unit 902 in Figure 8 can be implemented by the processor 801 in Figure 9 calling computer execution instructions stored in the memory 803. Or, Figure 8 the function / implementation process of the processing unit 902 in Figure 9The functions / implementation processes of the sending unit 901 and the receiving unit 903 in Figure 8 can be implemented through the communication interface 804 in

[0214] Optionally, when the device 900 is a chip or a circuit, the functions / implementation processes of the sending unit 901 and the receiving unit 903 can also be implemented through pins or circuits, etc.

[0215] This application also provides a computer-readable storage medium storing a computer program or instructions. When the computer program or instructions are run, the methods performed by the UE or the network device in the foregoing method embodiments are implemented. In this way, the functions described in the above embodiments can be implemented in the form of software function units and sold or used as independent products. Based on such an understanding, the technical solution of this application essentially, or the part that makes a contribution, or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may 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 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.

[0216] This application also provides a computer program product, which includes computer program code. When the computer program code runs on a computer, it causes the computer to execute the methods performed by the UE or the network device in any of the foregoing method embodiments.

[0217] This application embodiment also provides a processing device, including a processor and an interface; the processor is used to execute the methods performed by the UE or the network device involved in any of the foregoing method embodiments.

[0218] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0219] In the embodiments of the present application, the various illustrative logical units and circuits described can be implemented or operate the described functions through a design of a general-purpose processor, a digital signal processor (DSP), an ASIC, a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or any combination of the above. The general-purpose processor can include a microprocessor. Optionally, the general-purpose processor can also include any conventional processor, controller, microcontroller, or state machine. The processor can also be implemented through a combination of computing devices, such as a digital signal processor and a microprocessor, multiple microprocessors, one or more microprocessors combined with a digital signal processor core, or any other similar configuration.

[0220] The steps of the methods or algorithms described in the embodiments of the present application may be directly embedded in hardware, software units executed by a processor, or a combination of both. The software units may be stored in a RAM, flash memory, ROM, erasable programmable read-only memory (EPROM), EEPROM, register, hard disk, removable disk, CD-ROM, or any other form of storage medium in the art. Exemplarily, the storage medium may be connected to the processor so that the processor can read information from the storage medium and write information to the storage medium. Optionally, the storage medium may also be integrated into the processor. The processor and the storage medium may be disposed in an ASIC, and the ASIC may be disposed in a terminal device. Optionally, the processor and the storage medium may also be disposed in different components of the terminal device.

[0221] These computer program instructions may also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in a process Figure 1 a process or multiple processes and / or blocks Figure 1 steps of the functions specified in a block or multiple blocks.

[0222] The content in the various embodiments of the present application may be referred to each other. Without special instructions and logical conflicts, the terms and / or descriptions between different embodiments are consistent and may be cited mutually. The technical features in different embodiments may be combined to form new embodiments according to their inherent logical relationships.

[0223] It can be understood that in the embodiments of the present application, the UE and / or the network device may execute some or all of the steps in the embodiments of the present application. These steps or operations are only examples. In the embodiments of the present application, other operations or various deformations of the operations may also be executed. In addition, the various steps may be executed in different orders presented in the embodiments of the present application, and it is possible that not all the operations in the embodiments of the present application are to be executed.

Claims

1. A communication method, characterized in that, it includes: receiving first information, where the first information includes a first identifier and first configuration information, the first identifier is used to identify a feature, a function or a model, and the first configuration information is used to configure all or part of the models associated with N1 features, all or part of the models associated with N2 functions, or N3 models, the N1 features correspond to M1 functions, the M1 functions correspond to M2 models, and the M2 models are all or part of the models associated with the N1 features, and M1, M2, N1, N2, and N3 are all positive integers; applying the first configuration information to a first feature, a first function or a first model according to the first identifier, where the first feature is at least one of the N1 features, the first function is at least one of the N2 functions, and the first model is at least one of the N3 models.

2. The method according to claim 1, characterized in that, the first configuration information is used for at least one of data measurement or data reporting.

3. The method according to claim 1 or 2, characterized in that, the first information further includes a second identifier, and the second identifier is used to identify a feature, a function or a model; the method further includes: applying the first configuration information to a second feature, a second function or a second model according to the second identifier, where the second feature is at least one of the N1 features, the second feature is different from the first feature, the second function is at least one of the N2 functions, the second function is different from the first function, the second model is at least one of the N3 models, and the second model is different from the first model.

4. The method according to claim 1 or 2, characterized in that, the first information further includes a second identifier and second configuration information, the second identifier is used to identify a feature, a function or a model, and the second configuration information is used to configure all or part of the models associated with L1 features, all or part of the models associated with L2 functions, or L3 models, the L1 features correspond to K1 functions, the K1 functions correspond to K2 models, and the K2 models are all or part of the models associated with the L1 features, and K1, K2, L1, L2, and L3 are all positive integers; the method further includes: applying the second configuration information to a third feature, a third function or a third model according to the second identifier, where the third feature is at least one of the L1 features, the third function is at least one of the L2 functions, and the third model is at least one of the L3 models.

5. The method according to claim 1 or 2, characterized in that, the first configuration information is used to configure all or part of the models associated with the N1 features, and the first information further includes third configuration information, and the third configuration information is used to configure all or part of the models associated with the N1 features.

6. The method according to claim 5, characterized in that, Applying the first configuration information to the first feature according to the first identifier includes: According to the first identifier, configuring the first part of the model associated with the first feature with the first configuration information, and configuring the second part of the model associated with the first feature with the third configuration information; wherein, the first part of the model is different from the second part of the model.

7. The method according to any one of claims 1-6, characterized in that, before receiving the first information, the method further includes: sending a first request, the first request being used to request to configure the N1 features, the N2 functions or the N3 models; and / or, being used to request to provide P1 configurations for the N1 features, P2 configurations for the N2 functions or P3 configurations for the N3 models, where P1, P2 and P3 are all positive integers.

8. The method according to any one of claims 1-7, characterized in that, the first configuration information is used to configure all or part of the models associated with N1 features, all or part of the models associated with N2 functions or N3 models, including: the first configuration information is used to configure all or part of the models associated with the N1 features in the first stage, all or part of the models associated with the N2 functions in the first stage or all or part of the N3 models in the first stage; wherein, the first stage includes at least one of the following: training stage, inference stage or monitoring stage.

9. The method according to any one of claims 1-8, characterized in that, the first configuration information is used to configure all or part of the models associated with N1 features, all or part of the models associated with N2 functions or N3 models, including: the first configuration information is used to configure all or part of the models associated with the N1 features of the first requirement, all or part of the models associated with the N2 functions of the first requirement or all or part of the N3 models of the first requirement; wherein, the first requirement includes at least one of the following: high-precision requirement, medium-precision requirement or low-precision requirement.

10. A communication method, characterized in that, includes: determining first information, the first information including a first identifier and first configuration information, the first identifier being used to identify a feature, a function or a model, the first configuration information being used to configure all or part of the models associated with N1 features, all or part of the models associated with N2 functions or N3 models, the N1 features corresponding to M1 functions, the M1 functions corresponding to M2 models, the M2 models being all or part of the models associated with the N1 features, and M1, M2, N1, N2 and N3 are all positive integers; sending the first information.

11. The method according to claim 10, characterized in that, the first configuration information is used for at least one of data measurement or data reporting.

12. The method according to claim 10 or 11, characterized in that, the first information further includes a second identifier, the second identifier being used to identify a feature, a function or a model; Among them, the first configuration information is used to configure a second feature, a second function, or a second model, where the second feature is at least one of the N1 features, the second feature is different from the first feature, the second function is at least one of the N2 functions, the second function is different from the first function, the second model is at least one of the N3 models, and the second model is different from the first model.

13. The method according to claim 10 or 11, wherein, the first information further includes a second identifier and second configuration information, the second identifier is used to identify a feature, a function, or a model, and the second configuration information is used to configure all or part of the models associated with L1 features, all or part of the models associated with L2 functions, or L3 models, the L1 features correspond to K1 functions, the K1 functions correspond to K2 models, the K2 models are all or part of the models associated with the L1 features, and K1, K2, L1, L2, and L3 are all positive integers; Among them, the second configuration information is applied to a third feature, a third function, or a third model, where the third feature is at least one of the L1 features, the third function is at least one of the L2 functions, and the third model is at least one of the L3 models.

14. The method according to claim 10 or 11, wherein, the first configuration information is used to configure all or part of the models associated with the N1 features, and the first information further includes third configuration information, and the third configuration information is used to configure all or part of the models associated with the N1 features.

15. The method according to claim 14, wherein, the first configuration information is used to configure the first part of the models associated with the first feature, and the third configuration information is used for the second part of the models associated with the first feature; Among them, the first part of the models is different from the second part of the models.

16. The method according to any one of claims 10-15, wherein, before receiving the first information, the method further includes: receiving a first request, the first request is used to request to configure the N1 features, the N2 functions, or the N3 models; and / or, used to request to provide P1 configurations for the N1 features, P2 configurations for the N2 functions, or P3 configurations for the N3 models, and P1, P2, and P3 are all positive integers.

17. The method according to any one of claims 10-16, wherein, the first configuration information is used to configure all or part of the models associated with N1 features, all or part of the models associated with N2 functions, or N3 models, including: the first configuration information is used to configure all or part of the models associated with the N1 features in the first stage, all or part of the models associated with the N2 functions in the first stage, or all or part of the models associated with the N3 models in the first stage; Among them, the first stage includes at least one of the following: training stage, inference stage, or monitoring stage.

18. The method according to any one of claims 10-17, characterized in that, the first configuration information is used to configure all or part of the models associated with N1 features, all or part of the models associated with N2 functions, or N3 models, including: the first configuration information is used to configure all or part of the models associated with the N1 features of the first requirement, all or part of the models associated with the N2 functions of the first requirement, or the N3 models of the first requirement; wherein, the first requirement includes at least one of the following: high-precision requirement, medium-precision requirement, or low-precision requirement.

19. A communication device, characterized in that, it is used to implement the method according to any one of claims 1-9.

20. The communication device according to claim 19, characterized in that, the communication device includes a user equipment or a chip.

21. A communication device, characterized in that, it is used to implement the method according to any one of claims 10-18.

22. The communication device according to claim 21, characterized in that, the communication device includes a network device or a chip.

Images