Communication Method and Device

Abstract

Embodiments of this application provide a communication method and apparatus, which can solve the problem that a network device frequently sends configuration parameters of an artificial intelligence (AI) model and / or a machine learning (ML) model to a terminal device, thereby saving air interface overhead. This method can be applied to 4G systems, 5G systems, and / or future communication systems, such as 6G systems. The method includes: The terminal device receives configuration information of a first model from a first network device, and obtains first identification information for identifying the configuration of the first model. A second network device obtains the first identification information and sends first indication information to the terminal device. Then, the terminal device processes data using the configuration information of the first model. Among them, the first model is an artificial intelligence model or a machine learning model, and the first indication information is used to indicate to use the configuration information of the first model corresponding to the first identification information.

Description

Technical Field

[0001] Embodiments of the present application relate to the field of communications, and in particular, to a communication method and apparatus. Background Art

[0002] With the diversification of services supported by wireless networks, wireless networks need to meet various requirements such as ultra-high speed, ultra-low latency, ultra-high reliability, and / or ultra-large connection, which increases the complexity of network planning, network configuration, and resource scheduling.

[0003] Since artificial intelligence technology can simulate non-linear models and can effectively adapt to complex and changeable network environments. Therefore, in order to improve the management efficiency of wireless networks, artificial intelligence (AI) and / or machine learning (ML) can be introduced into wireless networks to achieve network intelligence and improve the management efficiency of the network. How to introduce artificial intelligence technology into wireless networks is a research topic worthy of study. Summary of the Invention

[0004] Embodiments of the present application provide a communication method and apparatus, which can introduce AI / ML technology into wireless networks, and network devices do not need to frequently send configuration parameters of AI models and / or ML models to terminal devices, thereby saving air interface overhead.

[0005] To achieve the above object, the present application adopts the following technical solutions:

[0006] In a first aspect, a communication method is provided. The communication method includes: receiving configuration information of a first model from a first network device, obtaining first identification information, receiving first indication information from a second network device, and processing data using the configuration information of the first model, where the first model is an artificial intelligence AI model or a machine learning ML model, the first identification information is used to identify the configuration of the first model, and the first indication information is used to indicate using the configuration information of the first model corresponding to the first identification information.

[0007] Based on the communication method described in the first aspect, the terminal device obtains the first identification information corresponding to the configuration of the first model existing in itself, and the second network device obtains the first identification information and sends the first indication information to the terminal device to instruct the terminal device to use the AI model or ML model existing in itself, which can avoid the second network device from sending the configuration parameters of the first model to the terminal device, thereby saving the signaling overhead of the air interface.

[0008] In a possible design, the obtaining of the first identification information may include: the configuration information of the first model includes the first identification information, or the first identification information is generated. That is to say, the terminal device may obtain the first identification information from the first network device, or the terminal device may assign or configure the corresponding identification information for the model it has (at this time, optionally, the obtaining of the first identification information may also be described as: determining the first identification information). In this way, the terminal device can obtain the correspondence between the configuration of the first model and the first identification information.

[0009] Optionally, the first identification information may include one or more of the following: the identification of the configuration information of the first model, the name of the first model, and the function of the first model. Exemplarily, the function of the first model may be for handover optimization, for encoding, for channel state information (CSI) feedback, etc. That is to say, there are various ways to identify the configuration of the first model. The terminal device can receive the first indication information indicating the configuration information of the first model corresponding to the first identification information, and use the first model for training and / or decision-making inference, which can avoid receiving the relatively large amount of corresponding model configuration parameters, thereby saving the signaling overhead of the air interface.

[0010] In a possible design, the configuration information of the first model may include the parameters of the first model, the hyperparameters of the first model, and / or the algorithm of the first model. Among them, the parameters of the first model are the configuration variables inside the first model, and the values of the parameters can be estimated using data. The hyperparameters of the first model are the configuration variables outside the model, and the values of the hyperparameters cannot be obtained using data estimation. In this way, the terminal device can process data using the configuration information of the first model, thereby realizing network intelligence.

[0011] In a possible design, the communication method described in the first aspect may further include: receiving second indication information from the first network device. Among them, the second indication information may be used to indicate the applicable range of the first model and / or the valid time of the first model. Optionally, the valid time of the first model may indicate the valid time range of the first model. In this way, the terminal device can determine the first model or the configuration information of the first model that it prefers or recommends to use according to the applicable range of the first model and / or the valid time of the first model.

[0012] Optionally, the applicable scope of the first model may include one or more of the following: information on the list of applicable public land mobile networks, information on the list of applicable cells, and applicable RRC states. Exemplarily, the information on the list of public land mobile networks may include one or more public land mobile networks. The cell list information may include a physical cell identifier (PCI), a cell global identifier (CGI), etc. The RRC state refers to the RRC state of the terminal device. The RRC state may include a connected state (RRC_connected), an idle state (RRC_idle), and / or an inactive state (RRC_inactive).

[0013] Optionally, the information on the list of public land mobile networks includes the registered public land mobile network of the terminal device. In this way, when the terminal device needs to use the model to process data, it can send the first identification information to the second network device to request the configuration information of the model that the terminal device currently has or prefers or is recommended to use, avoiding receiving the configuration parameters of the model, thereby reducing the signaling overhead of the air interface.

[0014] In a possible design, the first network device may be the same as the second network device. In this case, when the terminal device needs to use the model to process data, it can send the first identification information to the second network device to request the configuration information of the model that the terminal device currently has or prefers or is recommended to use, avoiding receiving the configuration parameters of the model, thereby reducing the signaling overhead of the air interface.

[0015] In a possible design, the first cell in the first network device may be the same as the second cell in the second network device. The first cell is the cell in which the first identification information is received, and the second cell is the cell in which the first identification information is sent.

[0016] That is, the terminal device can determine whether the first cell in the first network device is the same as the second cell in the second network device. If they are the same, the terminal device can send the first identification information to the second network device, so that the second network device can determine the model that the terminal device can use from the model corresponding to the first identification information, reducing the number of times of sending the configuration information of the first model to the terminal device and saving the signaling overhead of the air interface.

[0017] In a possible design, the cell list information may include a second cell. That is, the terminal device can determine whether the cell list information includes the second cell. If so, the terminal device sends first identification information to the second network device. In this way, it is possible to request the configuration information of the model that the terminal device currently has, prefers, or is recommended to use, avoiding receiving the configuration parameters of the model, thereby reducing the signaling overhead on the air interface.

[0018] In a possible design, the communication method described in the first aspect may further include: sending first identification information to the second network device. Optionally, the first identification information may indicate the model or the configuration information of the model that the terminal device currently has, prefers, or is recommended to use, so as to request to use the model or the configuration information of the model corresponding to the identification information. This method can avoid receiving the configuration parameters of the model, thereby reducing the signaling overhead on the air interface.

[0019] In a possible design, the communication method described in the first aspect may further include: receiving at least one second identification information from the second network device. The second identification information is used to indicate the model supported by the second network device or the configuration information of the supported model, and the model is an AI model or an ML model. In this way, the terminal device obtains the identification information corresponding to the model or the configuration information of the model supported by the second network device to determine whether to send the first identification information to the second network device. This method can reduce the complexity of the second network device in determining the first model that the terminal device can use and improve the efficiency of the terminal in processing data.

[0020] Optionally, the at least one second identification information may include the first identification information. That is, the terminal device can determine whether the at least one second identification information includes the first identification information. If so, the terminal device can send the first identification information to the second network device to request to use the model or model information corresponding to the first identification information to process data. This method can reduce the complexity of the second network device in determining the first model that the terminal device can use and improve the efficiency of the terminal in processing data.

[0021] Optionally, the model corresponding to the at least one second identification information may include the first model corresponding to the first identification information. That is, the terminal device can determine whether the model corresponding to the at least one second identification information includes the first model corresponding to the first identification information. If so, the first identification information is sent to the second network device to request to use the model or model information corresponding to the first identification information to process data. This method can reduce the complexity of the second network device in determining the first model that the terminal device can use and improve the efficiency of the terminal in processing data.

[0022] In a possible design, the communication method described in the first aspect may further include: sending first cell information to a second network device. The first cell information is used to indicate the cell in which the first identification information is received. In this way, the second network device can, based on the first cell information, learn the model corresponding to the first identification information or the configuration information of the model, and then determine whether the model corresponding to the first identification information or the configuration information of the model can be used by the terminal device. This method can improve the accuracy of the second network device in determining the first model that the terminal device can use.

[0023] In a possible design, the communication method described in the first aspect may further include: sending the first identification information and / or the configuration information of the first model to a core network element. In this way, the core network element can configure the first identification information and / or the configuration information of the first model for the second network device, so that the second network device can, based on the first identification information and / or the configuration information of the first model, determine the first model that the terminal device can use, avoiding the terminal device from receiving the configuration parameters of the model, thereby reducing the signaling overhead of the air interface.

[0024] In a possible design, the communication method described in the first aspect may further include: sending third indication information to a core network element; where the third indication information is used to indicate the applicable scope of the first model. In this way, the core network element can configure the applicable scope of the first model for the second network device. This method can enable the second network device to accurately determine the first model that the terminal device can use based on the applicable scope of the first model.

[0025] In a possible design, the communication method described in the first aspect may further include: sending the first identification information to a first network device. That is, if the first identification information is generated by the terminal device, the terminal device can send the first identification information to the first network device. This method can interact the correspondence between the model or the configuration of the model and the identification of the model between the terminal device and the first network device.

[0026] In a second aspect, a communication method is provided. The communication method includes: obtaining first identification information and sending first indication information to a terminal device. The first identification information is used to identify the configuration of a first model, the first model being an artificial intelligence (AI) model or a machine learning (ML) model, and the first indication information is used to indicate that the terminal device adopts the configuration information of the first model corresponding to the first identification information.

[0027] Optionally, the first identification information may include one or more of the following: an identifier of the configuration information of the first model, a name of the first model, and a function of the first model.

[0028] In a possible design, the configuration information of the first model may include the parameters of the first model, the hyperparameters of the first model, and / or the algorithm of the first model.

[0029] In a possible design, the sending of the first indication information to the terminal device may include: determining at least one third identification information, and if the at least one third identification information includes the first identification information, the first indication information may be sent to the terminal device. The third identification information may be used to indicate the first model available to the terminal device or the configuration information of the first model. In this way, it can be indicated to the terminal device which model or which model's configuration information to adopt, avoiding sending the configuration parameters of the model to the terminal device, thereby saving the signaling overhead of the air interface.

[0030] Optionally, if the at least one third identification information does not include the first identification information, the configuration information of at least one first model corresponding to the at least one third identification information may be sent to the terminal device.

[0031] In a possible design, the communication method described in the second aspect may further include: sending at least one second identification information to the terminal device. The second identification information may be used to indicate the model supported by the second network device or the configuration information of the supported model, and the model is an AI model or an ML model.

[0032] In a possible design, the obtaining of the first identification information may include: receiving the first identification information from the terminal device, or receiving the first identification information and / or the configuration information of the first model from the first network device, and receiving the first identification information and / or the configuration information of the first model from the core network element. The configuration information of the first model includes the first identification information. That is, the second network device can obtain information such as the first identification information, the parameters of the first model, the hyperparameters of the first model, the algorithm of the first model, and / or the applicable scope of the first model in various ways.

[0033] In a possible design, the communication method described in the second aspect may further include: receiving the first cell information from the terminal device. The first cell information may be used to indicate the cell in the first network device that sends the first identification information.

[0034] In addition, the technical effects of the communication method described in the second aspect may refer to the technical effects of the communication method described in the first aspect, which will not be elaborated here.

[0035] In a third aspect, a communication method is provided. The communication method includes: obtaining a first identification information and sending the first identification information to a second network device. The first identification information is used to identify the configuration of a first model, and the first model is an artificial intelligence (AI) model or a machine learning (ML) model.

[0036] Optionally, the first identification information may include one or more of the following: an identification of the configuration information of the first model, a name of the first model, and a function of the first model.

[0037] In a possible design, obtaining the first identification information may include: receiving the configuration information of the first model from a terminal device, or receiving the configuration information of the first model from a first network device. The configuration information of the first model may include the first identification information.

[0038] Optionally, the configuration information of the first model may include parameters of the first model and / or hyperparameters of the first model and / or an algorithm of the first model.

[0039] In a possible design, the communication method described in the third aspect may further include: receiving third indication information from the first network device. The third indication information is used to indicate the applicable scope of the first model.

[0040] In a possible design, the communication method described in the third aspect may further include: receiving third indication information from the terminal device.

[0041] Optionally, the applicable scope of the first model may include applicable public land mobile network list information and / or applicable cell list information.

[0042] In addition, the technical effects of the communication method described in the third aspect may refer to the technical effects of the communication method described in the first aspect, which will not be elaborated here.

[0043] In a fourth aspect, a communication method is provided. The communication method includes: sending the configuration information of the first model to a terminal device. The configuration information of the first model includes first identification information, and the first identification information is used to identify the configuration of the first model. The first model is an artificial intelligence (AI) model or a machine learning (ML) model.

[0044] Optionally, the first identification information may include one or more of the following: an identification of the configuration information of the first model, a name of the first model, and a function of the first model.

[0045] In a possible design, the configuration information of the first model may include parameters of the first model, hyperparameters of the first model, and / or an algorithm of the first model.

[0046] In a possible design, the communication method described in the fourth aspect may further include: sending second indication information to the terminal device. The second indication information may be used to indicate the applicable scope of the first model and / or the valid time of the first model.

[0047] Optionally, the applicable scope of the first model may include information on a list of applicable public land mobile networks and / or information on a list of applicable cells.

[0048] In a possible design, the communication method described in the fourth aspect may further include: sending configuration information of the first model to a core network element.

[0049] In a possible design, the communication method described in the fourth aspect may further include: sending third indication information to a core network element. The third indication information may be used to indicate the applicable scope of the first model.

[0050] In a possible design, the communication method described in the fourth aspect may further include: sending configuration information of the first model to a second network device.

[0051] In a possible design, the sending of the configuration information of the first model to the terminal device may include: sending the configuration information of the first model to the terminal device by means of broadcasting.

[0052] In a possible design, the communication method described in the fourth aspect may further include: receiving first identification information from a terminal device.

[0053] In addition, the technical effects of the communication method described in the fourth aspect may refer to the technical effects of the communication method described in the first aspect, which will not be elaborated here.

[0054] In a fifth aspect, a communication device is provided. The communication device includes: a processor. The processor is configured to execute the communication method described in any one of the possible implementation manners in the first aspect.

[0055] In a possible design, the communication device described in the fifth aspect may further include a memory. The memory is used to store computer programs or instructions. The processor is configured to read and run the instructions from the memory, so as to execute the communication method described in any one of the possible implementation manners in the first aspect.

[0056] In the present application, the communication device described in the fifth aspect may be a terminal device, or a chip (system) or other component or assembly that can be disposed in the terminal device.

[0057] In addition, the technical effects of the communication device described in the fifth aspect may refer to the technical effects of the communication method described in any one of the implementation manners in the first aspect, which will not be elaborated here.

[0058] In a sixth aspect, a communication device is provided. The communication device includes: a processor. The processor is configured to execute the communication method described in any one of the possible implementation manners in the second aspect.

[0059] In a possible design, the communication device described in the sixth aspect may further include a memory. The memory is used to store computer programs or instructions. The processor is used to read and run the instructions from the memory, so as to execute the communication method described in any one of the possible implementation manners in the second aspect.

[0060] In this application, the communication device described in the sixth aspect may be a second network device, or a chip (system) or other component or assembly that can be disposed in the second network device.

[0061] In addition, the technical effects of the communication device described in the sixth aspect may refer to the technical effects of the communication method described in any one of the implementation manners in the first aspect, which will not be elaborated here.

[0062] The seventh aspect provides a communication device. The communication device includes: a processor. The processor is used to execute the communication method described in any one of the possible implementation manners in the third aspect.

[0063] In a possible design, the communication device described in the seventh aspect may further include a memory. The memory is used to store computer programs or instructions. The processor is used to read and run the instructions from the memory, so as to execute the communication method described in any one of the possible implementation manners in the third aspect.

[0064] In this application, the communication device described in the seventh aspect may be a core network element, or a chip (system) or other component or assembly that can be disposed in the core network element.

[0065] In addition, the technical effects of the communication device described in the seventh aspect may refer to the technical effects of the communication method described in any one of the implementation manners in the first aspect, which will not be elaborated here.

[0066] The eighth aspect provides a communication device. The communication device includes: a processor. The processor is used to execute the communication method described in any one of the possible implementation manners in the fourth aspect.

[0067] In a possible design, the communication device described in the eighth aspect may further include a memory. The memory is used to store computer programs or instructions. The processor is used to read and run the instructions from the memory, so as to execute the communication method described in any one of the possible implementation manners in the fourth aspect.

[0068] In this application, the communication device described in the eighth aspect may be a first network device, or a chip (system) or other component or assembly that can be disposed in the first network device.

[0069] In addition, the technical effects of the communication device described in the eighth aspect may refer to the technical effects of the communication method described in any one of the implementation manners in the first aspect, which will not be elaborated here.

[0070] In a ninth aspect, a communication system is provided. The system includes a terminal device, a first network device, and a second network device.

[0071] Optionally, the communication system may further include a core network element.

[0072] Optionally, the first network device may be the same as the second network device.

[0073] In an eleventh aspect, a computer-readable storage medium is provided, including: the computer-readable storage medium includes a computer program or instruction; when the computer program or instruction runs on a computer, the computer is caused to execute the method of the communication device according to any one of the possible implementation manners in the first aspect to the fourth aspect.

[0074] In a twelfth aspect, a computer program product is provided, including a computer program or instruction, when the computer program or instruction runs on a computer, the computer is caused to execute the method of the communication device according to any one of the possible implementation manners in the first aspect to the fourth aspect. Description of the Drawings

[0075] Figure 1 It is a schematic diagram of the architecture of the communication system provided by the embodiment of the present application;

[0076] Figure 2 It is a schematic diagram of the physical architecture of the access network device provided by the embodiment of the present application;

[0077] Figure 3 It is a schematic diagram of the structure of the communication device provided by the embodiment of the present application Figure 1 ;

[0078] Figure 4 It is a schematic diagram of the process of the communication method provided by the embodiment of the present application Figure 1 ;

[0079] Figure 5 It is a schematic diagram of the process of the communication method provided by the embodiment of the present application Figure 2 ;

[0080] Figure 6 It is a schematic diagram of the process of the communication method provided by the embodiment of the present application Figure 3 ;

[0081] Figure 7 It is a schematic diagram of the process of the communication method provided by the embodiment of the present application Figure 4 ;

[0082] Figure 8 It is a schematic diagram of the process of the communication method provided by the embodiment of the present application Figure 5 ;

[0083] Figure 9 Flow schematic of the communication method provided by the embodiment of the present application Figure 6 ;

[0084] Figure 10 Structure schematic of the communication device provided by the embodiment of the present application Figure 2 ;

[0085] Figure 11 Structure schematic of the communication device provided by the embodiment of the present application Figure 3 ;

[0086] Figure 12 Structure schematic of the communication device provided by the embodiment of the present application Figure 4 ;

[0087] Figure 13 Structure schematic of the communication device provided by the embodiment of the present application Figure 5 。 Detailed implementation manners

[0088] Next, the technical solutions in the present application will be described in conjunction with the accompanying drawings.

[0089] The technical solutions of the embodiments of the present application can be applied to various communication systems, such as wireless fidelity (WiFi) systems, vehicle to everything (V2X) communication systems, device-to-device (D2D) communication systems, vehicle networking communication systems, 4th generation (4G) mobile communication systems, such as long term evolution (LTE) systems, worldwide interoperability for microwave access (WiMAX) communication systems, 5th generation (5G) mobile communication systems, such as new radio (NR) systems, and / or future communication systems, such as 6th generation (6G) mobile communication systems, etc.

[0090] The present application will present various aspects, embodiments or features around a system that may include multiple devices, components, modules, etc. It should be understood and clear that each system may include additional devices, components, modules, etc., and / or may not include all the devices, components, modules, etc. discussed in conjunction with the accompanying drawings. In addition, combinations of these solutions can also be used.

[0091] In addition, in the embodiments of the present application, words such as "exemplarily" and "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as an "example" in the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of the word "example" is intended to present concepts in a specific manner.

[0092] In the embodiments of the present application, "information", "data", "signal", "message", "channel", and "signalling" may sometimes be used interchangeably. It should be noted that when the differences are not emphasized, their intended meanings are the same. "Of", "corresponding", and "corresponding" may sometimes be used interchangeably. It should be noted that when the differences are not emphasized, their intended meanings are the same.

[0093] The network architecture and service scenarios described in the embodiments of the present application are for more clearly illustrating the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those of ordinary skill in the art will know that with the evolution of the network architecture and the emergence of new service scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

[0094] Figure 1 It is a schematic diagram of the architecture of a communication system applicable to the communication method provided by the embodiments of the present application. To facilitate the understanding of the embodiments of the present application, first, Figure 1 the communication system shown in is taken as an example to describe in detail the communication system applicable to the embodiments of the present application. It should be noted that the solutions in the embodiments of the present application can also be applied to other mobile communication systems, and the corresponding names can also be replaced with the names of the corresponding functions in other mobile communication systems.

[0095] As Figure 1 shown, the communication system includes a first network device, a second network device, and a terminal device. Optionally, the communication system may further include a core network element.

[0096] Among them, the above-mentioned first network device and second network device are devices located on the network side of the above-mentioned communication system and having wireless transceiver functions, or chips or chip systems that can be set in the devices. The above-mentioned first network device and second network device can be access network devices, and the access network devices include, but are not limited to: access points (APs) in a wireless fidelity (WiFi) system (such as home gateways, routers, servers, switches, bridges, etc.), base stations, evolved Node Bs (eNBs), radio network controllers (RNCs), Node Bs (NBs), base station controllers (BSCs), base transceiver stations (BTSs), home base stations (for example, home evolved Node Bs, or home Node Bs, HNBs), baseband units (BBUs), wireless relay nodes, wireless backhaul nodes, or transmission and reception points (TRP or TP), etc. The access network device can also be for 5G, such as gNBs, transmission points (TRP or TP) in a new radio (NR) system, one or a group of antenna panels of a base station in a 5G system (including multiple antenna panels), or can be network nodes constituting a gNB or a transmission point, such as a baseband unit (BBU), or a central unit (CU), or a distributed unit (DU), a roadside unit (RSU) with base station functions, etc. The central unit CU can include a control plane (central unit-control plane, CU-CP) and a user plane (central unit-user plane, CU-UP). Alternatively, the above-mentioned first network device and second network device can be a network device or network element logically located above the access network device, such as an artificial intelligence control / controller (AIC) or a radio intelligence control / controller (RIC), etc. The first network device and the second network device communicate with the terminal device through the access network device.

[0097] Figure 2Schematic diagram of the physical architecture of the access network device provided by the embodiments of the present application. The above-mentioned first network device and second network device can be implemented by using the physical architecture shown in Figure 2 . As shown in Figure 2As shown, the access network device may include a central unit (CU) and a distributed unit (DU). For example, part of the functions of the access network device are deployed in the CU, and the remaining functions are deployed in the DU. Multiple DUs can share one CU. This design can save costs and facilitate network expansion. Specifically, the split of the CU and DU can be based on the protocol stack. A possible implementation is to deploy the radio resource control (RRC) layer, service data adaptation protocol (SDAP) layer, and packet data convergence protocol (PDCP) layer in the CU, and deploy the radio link control (RLC) layer, media access control (MAC) layer, and physical layer (PHY) in the DU. The CU and DU are connected through the F1 interface. The CU can be connected to the core network through the NG interface on behalf of the gNB. The CU can be connected to other gNBs through the Xn interface on behalf of the gNB. The CU can be connected to other base stations (such as eNBs) through the X2 interface on behalf of the gNB to perform dual connection operations. Further, the central unit CU may include a control plane CU-CP and a user plane CU-UP. Among them, CU-CP is responsible for control plane functions. For example, CU-CP can implement the functions of the RRC layer and the PDCP layer corresponding to the control plane (i.e., PDCP-C). PDCP-C can be responsible for encryption, decryption, integrity protection, and / or data transmission of control plane data. CU-UP is responsible for user plane functions. For example, it can implement the functions of the SDAP layer and the PDCP layer corresponding to the user plane (i.e., PDCP-U). Among them, the SDAP layer is mainly responsible for processing the data of the core network and mapping the flow to the bearer. PDCP-U is mainly responsible for encryption, decryption, integrity protection, header compression, sequence number maintenance, and / or data transmission of user plane data. Among them, CU-CP and CU-UP are connected through the E1 interface. CU-CP can be connected to the core network through the NG interface on behalf of the gNB. CU-CP is connected to the DU through the control plane of the F1 interface (i.e., F1-C). CU-UP is connected to the DU through the user plane of the F1 interface (i.e., F1-U). Another possible implementation is to deploy PDCP-C in CU-UP. It should be noted that CU, DU, CU-CP, and / or CU-UP may also use other names, such as the T1 device, equipment, or network element. The embodiments of this application do not limit this. Among them, T1 is a positive integer. For different devices, the value of T1 may be different.

[0098] The above terminal device is a terminal with a wireless transceiver function for accessing the above communication system, or a chip or chip system that can be set in the terminal. The terminal device can also be referred to as a user equipment (UE), user device, access terminal, user unit, user station, mobile station (MS), remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device. The terminal device in the embodiments of the present application can be a mobile phone, a tablet computer (Pad), a computer with a wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, an in-vehicle terminal, or an RSU with terminal functions, etc. The terminal device in the embodiments of the present application can be an in-vehicle module, in-vehicle module group, in-vehicle component, in-vehicle chip or in-vehicle unit that is built-in or installed in a vehicle as one or more components or units. For example, the vehicle can implement the communication method provided in the present application by means of the in-vehicle module, in-vehicle module group, in-vehicle component, in-vehicle chip or in-vehicle unit that is built-in or installed.

[0099] The above core network element is a device located on the network side of the above communication system, and provides network services for the terminal device through the first network device and / or the second network device, or a chip or chip system that can be disposed in the device. The core network element may also be referred to as a core network device. The core network element in the embodiments of the present application may be an access and mobility management function (AMF) entity, a session management function (SMF) entity, a user plane function (UPF) entity, etc., which are not listed one by one here. Among them, the AMF entity may be responsible for the access management and mobility management of the terminal device; the SMF entity may be responsible for session management, such as session establishment of the terminal device, etc.; the UPF entity may be a functional entity of the user plane, mainly responsible for connecting to the external network. It should be noted that the entity in the embodiments of the present application may also be referred to as a network element or a functional entity. For example, the AMF entity may also be referred to as an AMF network element or an AMF functional entity. For another example, the SMF entity may also be referred to as an SMF network element or an SMF functional entity, etc.

[0100] It should be noted that the communication method provided in the embodiments of the present application may be applicable to or assist in Figure 1 communication between any two nodes shown, such as between the terminal device and the first network device, between the terminal device and the second network device, between the terminal device and the core network element, between the first network device and the second network device, between the first network device and the core network element, and between the second network device and the core network element.

[0101] It should be understood that Figure 1 only a simplified schematic diagram shown for ease of understanding. The communication system may further include other network devices, and / or other terminal devices, Figure 1 which are not drawn in the figure.

[0102] Figure 3 is a structural schematic Figure 1 of a communication device that can be used to execute the communication method provided in the embodiments of the present application. The communication device may be a terminal device, or a chip (system) or other components or assemblies applicable to the terminal device. Or, the communication device may be the first network device, or a chip (system) or other components or assemblies applicable to the first network device. Or, the communication device may be the second network device, or a chip (system) or other components or assemblies applicable to the second network device. Or, the communication device may also be a core network element, or a chip (system) or other components or assemblies applicable to the core network element.

[0103] Such asFigure 3 As shown in Figure 3 , the communication device 300 includes a processor 301. Optionally, the communication device 300 may further include a communication interface 302 and a memory 303. Among them, the processor 301 may be integrated with the communication interface 302 or exist independently. The memory 303 may be integrated with the processor 301 or exist independently. The embodiments of the present application do not make specific limitations on this.

[0104] Next, in combination with Figure 3 the following, a specific introduction to each component of the communication device 300 will be given:

[0105] The processor 301 is the control center of the communication device 300, which may be a single processor or a collective term for multiple processing elements. For example, the processor 301 is one or more central processing units (CPUs), or may be an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application, such as: one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs).

[0106] Optionally, the processor 301 may execute various functions of the communication device 300 by running or executing software programs or instructions stored in the memory 303, and optionally, by calling data stored in the memory 303.

[0107] In a specific implementation, as an embodiment, the processor 301 may include one or more CPUs, such as Figure 3 the CPU0 and CPU1 shown in Figure 3 .

[0108] In a specific implementation, as an embodiment, the communication device 300 may also include multiple processors, such as Figure 3 the processor 301 and the processor 304 shown in Figure 3 . Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). Here, the processor may refer to one or more communication devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0109] The memory 303 may be a read-only memory (ROM) or other types of static storage communication devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage communication devices that can store information and instructions, 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 communication 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 is not limited thereto.

[0110] Optionally, the memory 303 is used to store the software program or instructions for implementing the embodiments of the present application and is controlled by the processor 301 for execution. The above specific implementation manners can refer to the following method embodiments and will not be elaborated herein.

[0111] The communication interface 302 can be a transceiver circuit, a bus, a module, a pin, etc., for communicating with other communication devices. For example, if the communication device 300 is a terminal device, the communication interface 302 can be used to communicate with a first network device, or with a second network device, or with a core network element. Another example is that if the communication device 300 is a first network device, the communication interface 302 can be used to communicate with a terminal device, or with a second network device, or with a core network element. Still another example is that if the communication device 300 is a second network device, the communication interface 302 can be used to communicate with a first network device, or with a terminal device, or with a core network element. Yet another example is that if the communication device 300 is a core network element, the communication interface 302 can be used to communicate with a first network device, or with a second network device, or with a terminal device. In addition, the transceiver circuit can be a device such as a transceiver or a transceiver. The communication interface 302 can also be an input / output (I / O) circuit of the processor 301 to implement the signal input and signal output of the processor 301.

[0112] It should be noted that Figure 3 the structure of the communication device 300 shown in

[0113] When introducing AI / ML technologies into wireless networks, a large amount of data can be obtained, and AI / ML algorithms can be used to train models and / or perform decision-making inferences on the obtained data, thereby outputting AI / ML models and / or decision results. In this way, network functions can be implemented or assisted by using AI / ML. For example, AI / ML technologies can be used to predict the amount of service data within a certain period in the future, thereby realizing network intelligence.

[0114] In a possible implementation, the network device sends the configuration parameters of the AI model or the configuration parameters of the ML model to the terminal device. Then, the terminal device uses the AI model or the ML model for training and / or decision-making inference. Moreover, every time the terminal device needs to use the AI model or the ML model, the network device needs to send the corresponding model configuration parameters to it. However, the data volume of the configuration parameters of the AI model or the ML model is relatively large. Frequent sending of the configuration parameters of the AI model or the ML model by the network device to the terminal device will cause excessive overhead on the air interface.

[0115] The following will be combined with Figures 4 - 8 to specifically elaborate on the communication method provided in the embodiments of the present application.

[0116] Figure 4 is a schematic flowchart of the communication method provided in the embodiments of the present application Figure 1 .

[0117] As Figure 4 shown, the communication method includes the following steps:

[0118] S401, the first network device sends the configuration information of the first model to the terminal device. Correspondingly, the terminal device receives the configuration information of the first model from the first network device.

[0119] The first model can be used for model training and / or inference. Exemplarily, the first model is an artificial intelligence (AI) model or a machine learning (ML) model.

[0120] The terminal device can perform inference using the first model.

[0121] The terminal device can further use the first model for training to obtain an updated model. Optionally, the terminal device can send the parameter information of the trained model to the network device, for example, for federated training, etc.

[0122] The following elaborates on the artificial intelligence model and the machine learning model.

[0123] An artificial intelligence model is an algorithmic model. Artificial intelligence can simulate human consciousness and thinking processes, enabling machines to have the ability to solve problems that humans can solve through experience. For example, natural language understanding, image recognition, playing chess, etc.

[0124] Machine learning is a method that can endow machines with learning capabilities, enabling them to perform functions that cannot be achieved through direct programming. Specifically, by providing a large amount of training data to the learning algorithm, the learning algorithm generates a new rule or algorithm, namely a machine learning model, based on inferences from the data, and this model can then be used for prediction. In the embodiments of this application, using the model for prediction can also be referred to as using the model for decision-making and / or reasoning, etc. Machine learning algorithms include deep learning, support vector machines, linear regression, logistic regression, and K-nearest neighbor algorithms, etc., without limitation.

[0125] Exemplarily, deep learning is machine learning using deep neural networks. A neural network is a network consisting of three types of computational layers: an input layer, hidden layers, and an output layer. Each layer has one or more logical judgment units, and such logical judgment units are called neurons. Each neuron weights (the corresponding weights can be called weights) each input value and sums them. A deep neural network is a neural network with an input layer, multiple hidden layers, and an output layer.

[0126] Exemplarily, the core idea of support vector machines (SVM) is to obtain a separating hyperplane that can correctly divide the training data set and has the largest geometric margin. Some data in the data samples that are closest to the separating hyperplane are called support vectors.

[0127] Exemplarily, linear regression is a statistical analysis method that uses regression analysis in mathematical statistics to determine the quantitative relationship of interdependence between two or more variables. The process of linear regression is to find the optimal model to describe the data, and the mean squared error can be used as a measure of the model performance. The mean squared error refers to the average variance between the predicted value and the actual value. The smaller the average variance, the smaller the gap between the test value and the actual value, that is, the better the model performance.

[0128] Exemplarily, logistic regression is a classification algorithm that can establish a binomial type of model for data with one or more explanatory variables, estimate probabilities using the logistic function of the cumulative logistic distribution, and measure the relationship between the categorical dependent variable and one or more independent variables. Logistic regression is a non-linear regression model.

[0129] Exemplarily, the K-nearest neighbor algorithm is a classification algorithm. Its core idea is that in the feature space, if most of the K samples that are most similar to the current sample (i.e., the nearest in the feature space) belong to a certain category, then this sample also belongs to this category and has the characteristics of the samples in this category.

[0130] Exemplarily, federated training is a type of distributed training. In federated training, a central node (such as a network device) sends an AI model to multiple participating nodes (such as terminal devices). The participating nodes perform AI model training based on this AI model and the data they collect or measure, and report the AI model they trained to the central node in the form of gradients. The central node processes the gradient information fed back by the participating nodes (such as averaging or other operations) to obtain a new AI model. Optionally, the central node can send this new AI model to multiple participating nodes, so that these multiple participating nodes can perform AI model training based on this AI model and the data they collect or measure. The central node can obtain an updated AI model again according to the gradient information fed back by the participating nodes. In federated learning, the participating nodes in each training process may be the same or different, which is not limited in the embodiments of this application. This method places the training process on multiple devices instead of aggregating it on a server, solving the problems of long training time and large communication overhead in centralized training. Among them, centralized training is performed by a single node (such as a network device, RIC, or server).

[0131] In some embodiments, the first network device may send configuration information of at least one first model to the terminal device. Correspondingly, the terminal device may receive the configuration information of at least one first model from the first network device. For the sake of convenience of description, the AI / ML model may be simply referred to as the AI model hereinafter.

[0132] That is to say, the first network device may send configuration information of one or more AI models to the terminal device, and this application does not limit the number and type of models. Among them, different models can implement different network functions. The network functions include but are not limited to: radio access technology (RAT) selection, load balancing, mobility management, network energy saving, coverage optimization, flow control, scheduling, channel coding, or modulation, etc., without limitation.

[0133] In some embodiments, the configuration information of the first model may include first identification information, and the first identification information may be used to identify the configuration of the first model. In the embodiments of this application, that the first identification information can be used to identify the configuration of the first model can also be described as: the first identification information can be used to identify the configuration information of the first model.

[0134] In some embodiments, the configuration information of the first model may not include the first identification information, and the first network device sends the first identification information and / or the configuration information of the first model to the terminal device.

[0135] Optionally, the first identification information includes, but is not limited to, one or more of the following: the identification of the configuration information of the first model, the name of the first model, and the function of the first model.

[0136] Among them, the function of the first model includes those for implementing or assisting in implementing: RAT selection, load balancing, mobility management (such as handover optimization), network energy saving, coverage optimization, flow control, scheduling, channel coding, modulation, or channel state information (CSI) feedback, etc., without limitation. The identification of the configuration information of the first model can be any identification that can identify the first model or the configuration information of the first model. The name of the first model can be any name that can identify the first model or the configuration information of the first model, such as a classification model, a regression-related model, etc.

[0137] Exemplarily, assuming that the identification of the configuration information of the first model is 1, the name of the first model is AI Model 1, and the function of the first model is coding, then a combination of one or more of 1, AI Model 1, and coding can be used to uniquely identify the first model or the configuration of the first model.

[0138] That is to say, any one of the identification of the configuration information of the first model, the name of the first model, and the function of the first model can be used to uniquely identify the configuration of the AI model or the ML model, or any combination of the identification of the configuration information of the first model, the name of the first model, and the function of the first model can be used to uniquely identify the configuration of the AI model or the ML model. Embodiments of this application do not limit the implementation manner of identifying the configuration of the first model, as long as it can identify the configuration of the first model.

[0139] In some embodiments, the configuration information of the first model may include the parameters of the first model, the hyperparameters of the first model, and / or the algorithm of the first model. In one possible implementation, the parameters of the first model and the hyperparameters of the first model can be collectively referred to as the parameters of the first model.

[0140] The parameters of the first model, the hyperparameters of the first model, and the algorithm of the first model will be specifically elaborated below.

[0141] Exemplarily, the parameters of the first model are configuration variables inside the first model. The values of the parameters can be obtained by data estimation. For example, the parameter can be one or more of the following: weights in a neural network (i.e., weighting coefficients for input values), activation functions (i.e., operation functions on neurons in a neural network), topologies in a neural network (i.e., how many layers a neural network has, how many neurons each layer has, and / or the relationships between neurons before each layer, etc.), support vectors in a support vector machine, coefficients in linear regression, and coefficients in logistic regression.

[0142] Specifically, the parameter has one or more of the following characteristics: the parameter is obtained from data estimation or data learning, the parameter is usually not manually configured by a programmer, the parameter is usually saved as part of the model, the model can use the parameter during training or inference, and the value of the parameter defines the model that can be used.

[0143] Exemplarily, the hyperparameters of the first model are configuration variables outside the model. The values of the hyperparameters cannot be obtained by data estimation. For example, the hyperparameter can be the learning rate for training a neural network, the penalty parameter and sigma hyperparameter (sigma is related to the number of support vector machines) in a support vector machine, and K in the K-nearest neighbor algorithm.

[0144] Specifically, the hyperparameter has one or more of the following characteristics: the hyperparameter is usually applied in the process of estimating model parameters, the hyperparameter is usually directly specified by a practitioner, the hyperparameter can usually be set using heuristic methods, and the hyperparameter is usually adjusted according to a given predictive modeling problem.

[0145] Exemplarily, the algorithm of the first model refers to the input parameters of the algorithm that a network element (such as a terminal device) needs to use when performing training or inference. For example, for the Q-learning algorithm, the core is a Q-table. The rows and columns of this table represent states and actions respectively. What is saved in the Q-table is the expectation of obtaining rewards (referred to as Q-values) when corresponding actions are taken in each state. Suppose the Q-table includes m states and n actions, then the size of the Q-table is m * n.

[0146] For inference using the Q-learning algorithm, the network element (such as a terminal device) that performs inference using Q-learning first determines the current state, looks up the Q-value corresponding to the current state, selects the action with the largest Q-value to complete an inference process, and then enters the next state and performs inference in a similar way. That is to say, for inference, the input parameter of the Q-learning algorithm is the initial content in the Q-table.

[0147] For training using the Q-learning algorithm, a network element (such as a terminal device) trained using Q-learning calculates the optimal Q value by exploring and updating the Q values in the Q-table multiple times. The network element can use a certain algorithm to update the Q values in the Q-table. For example, when the network element is in state S0, it selects action A0 and then enters state S1, and updates the Q value corresponding to state S0 and action A0. For example, the following formula can be used to update the Q value corresponding to state S0 and action A0: Q(S0,A0)_new = Q(S0,A0)_old + a * (Q(S0,A0)_target - Q(S0,A0)_old). Where, Q(S0,A0)_new is the updated Q value corresponding to state S0 and action A0, and Q(S0,A0)_old is the Q value corresponding to state S0 and action A0 before the update. Q(S0,A0)_target = R(S1) + y * max{Q(S1,b)}, R(S1) is the reward that the network element can obtain when entering S1 by adopting action A0 in state S0, y is the attenuation value, max{Q(S1,b)} is the maximum Q value among the Q values corresponding to all possible actions in state S1, and a is the learning rate. That is to say, the input parameters of the Q-learning algorithm are the initial content in the Q-table, and the values of R(.), y, and a, where R(.) is the reward that the network element can obtain.

[0148] It should be noted that the first network device sending the configuration information of the first model to the terminal device may mean that the first network device sends the configuration information of the first model to the terminal device through one or more messages. For example, the first network device sends the parameters of the first model and / or the hyperparameters of the first model and / or the algorithm of the first model through the first message, and sends the first identification information through the second message. Another example is that the first network device sends the configuration information of at least one first model to the terminal device through a broadcast message, and the configuration information of the first model includes the parameters of the first model and / or the hyperparameters of the first model and / or the algorithm of the first model and the first identification information.

[0149] In some embodiments, the configuration information of the first model may include the applicable scope of the first model and / or the valid time of the first model.

[0150] Exemplarily, the applicable scope of the first model may include one or more of the following: (list) information of the applicable public land mobile network (PLMN), (list) information of the applicable cell, and the applicable RRC state. Wherein, the list information means that this information can be represented in the form of a list.

[0151] Among them, the public land mobile network list information may include one or more public land mobile networks PLMN.

[0152] The cell list information may include the physical cell identifier (PCI) of one or more cells, or the global cell identifier (CGI), etc.

[0153] The RRC state refers to the RRC state of the terminal device. The RRC state may include the connected state (RRC_connected), the idle state (RRC_idle), and / or the inactive state (RRC_inactive). That is, the first model can be used only when the terminal device is in the corresponding RRC state.

[0154] Specifically, the valid time of the first model may indicate the valid time range of the first model.

[0155] Optionally, when the terminal device receives the valid time of the first model from the first network device, the terminal device may start a timer, and the length of the timer is the value of the valid time of the first model. When the timer expires, the terminal device stops using the configuration information of the first model to process data.

[0156] It should be noted that the configuration information of the first model may include one or more of the first identification information, the parameters of the first model, the hyperparameters of the first model, the algorithm of the first model, the applicable range of the first model, and the valid time of the first model. Other contents not included may be determined by protocol convention or other means, which are not limited. For example, the configuration information of the first model may include the first identification information, the parameters of the first model, the algorithm of the first model, and the applicable range of the first model. Another example is that the configuration information of the first model may include the valid time of the first model, and the embodiments of the present application will not list them one by one.

[0157] Exemplarily, the configuration of the first model may include the parameters of the first model, the hyperparameters of the first model, the algorithm of the first model, and may also include the applicable range of the first model and / or the valid time of the first model.

[0158] In a possible design, the first network device may indicate the applicable range and / or the valid time of the first model to the terminal device through other information. For example, the first network device may send second indication information to the terminal device. Correspondingly, the terminal device may receive the second indication information from the first network device. At this time, the applicable range and / or the valid time of the first model may be indicated by both the configuration information of the first model and the second indication information, or indicated by the second indication information without passing through the configuration information of the first model.

[0159] Optionally, the second indication information may be used to indicate the applicable range and / or the valid time of the first model.

[0160] It should be noted that the first network device may send the second indication information to the terminal device in a broadcast manner (such as through a master information block (MIB), a system information block (SIB), or other common messages), or the first network device may send the second indication information to the terminal device in a unicast manner (or a dedicated message, such as a dedicated RRC message). This application does not limit this.

[0161] The following combines Figure 2 with the physical architecture of the access network device shown in the figure to further illustrate the specific implementation manner of the first network device sending the configuration information of the first model and the second indication information to the terminal device.

[0162] Combined with Figure 2 , the first network device may be Figure 2 the access network device shown in the figure. The DU of the access network device may configure the configuration information of the first model and / or the second indication information for the terminal device. Specifically, the DU of the access network device may send the configuration information of the first model and / or the second indication information to the CU or CU-CP of the access network device through the F1-C interface. Then, the CU or CU-CP of the access network device sends the configuration information of the first model and / or the second indication information to the terminal device through the air interface. For example, the CU or CU-CP of the access network device generates an RRC message and sends the RRC message to the DU of the access network device. The RRC message includes the configuration information of the first model and / or the second indication information, and then the DU of the access network device sends the RRC message to the terminal device through the air interface.

[0163] Alternatively, combined with Figure 2 , the first network device may be Figure 2 the access network device shown in the figure. The CU of the access network device may configure the configuration information of the first model and / or the second indication information for the terminal device. Specifically, the CU or CU-CP of the access network device sends the configuration information of the first model and / or the second indication information to the terminal device through the air interface. For example, the CU or CU-CP of the access network device generates an RRC message and sends the RRC message to the DU of the access network device. The RRC message includes the configuration information of the first model and / or the second indication information, and then the DU of the access network device sends the RRC message to the terminal device through the air interface.

[0164] When the access network device adopts a physical architecture different from Figure 2 the one shown in the figure, the specific implementation manner of the first network device sending the configuration information of the first model and / or the second indication information to the terminal device may be different.

[0165] Exemplarily, in addition to the CU and DU shown in Figure 2 the access network device's physical architecture may further include an AIC. The first network device may be the access network device including the CU, DU, and AIC. The AIC of the access network device configures the configuration information of the first model and / or the second indication information for the terminal device. Specifically, the AIC may be deployed above the CU. The AIC of the access network device may send the configuration information of the first model and / or the second indication information to the CU or CU-CP of the access network device. Then, the CU or CU-CP of the access network device sends the configuration information of the first model and the second indication information to the terminal device through the air interface. For example, the CU or CU-CP of the access network device generates an RRC message, which includes the configuration information of the first model and / or the second indication information, and sends the RRC message to the DU of the access network device, and then the DU of the access network device sends the RRC message to the terminal device through the air interface.

[0166] When the first network device is not an access network device, such as when the first network device is an AIC and the AIC does not belong to the access network device, the specific implementation manner for the above-mentioned first network device to send the configuration information of the first model and / or the second indication information to the terminal device is as follows.

[0167] Exemplarily, different from the AIC being deployed inside the access network device, the AIC may be a different network device from the access network device. The AIC configures the configuration information of the first model and / or the second indication information for the terminal device. Specifically, the AIC sends the configuration information of the first model and / or the second indication information to the access network device, and then the access network device sends the configuration information of the first model and / or the second indication information to the terminal device.

[0168] In a possible design, the first network device may send the first identification information or the configuration information of the first model to the second network device.

[0169] That is to say, the model existing in the terminal device or the configuration information of the existing model can be indicated through the first identification information, or the model or the configuration information that the terminal device prefers or is recommended to use can be indicated. When the configuration information of the first model includes information such as the parameters of the first model, the hyperparameters of the first model, the algorithm of the first model, the applicable range of the first model, and / or the valid time of the first model, the second network device can learn the configuration information of the first model that the first network device has sent to the terminal device, and the second network device can learn the corresponding configuration information.

[0170] Exemplarily, when the terminal device undergoes a handover, from cell 1 to cell 2, where cell 1 is managed by a first network device and cell 2 is managed by a second network device, the first network device may send the first identification information or the configuration information of the first model to the second network device.

[0171] In some embodiments, the first network device may send third indication information to the second network device. Correspondingly, the second network device may receive the third indication information from the first network device.

[0172] Exemplarily, the third indication information may be used to indicate the applicable scope of the first model. That is, the first network device may send the applicable scope of the first model to the second network device through the third indication information. At this time, the applicable scope of the first model may be indicated by both the configuration information of the first model and the third indication information, or indicated by the third indication information without the configuration information of the first model.

[0173] Optionally, the first network device may send the third indication information to the second network device in a scenario where the terminal device undergoes a handover, such as when the terminal device handovers from cell 1 to cell 2, where cell 1 is managed by the first network device and cell 2 is managed by the second network device.

[0174] In some embodiments, the first network device may send first cell information to the second network device. Correspondingly, the second network device may receive the first cell information from the first network device.

[0175] Optionally, the first cell information may be used to indicate the cell in which the first network device sends the first identification information and / or the configuration information of the first model to the terminal device. Exemplarily, the first cell information may include the physical cell identifier (PCI) corresponding to the cell in which the first network device sends the configuration information of the first model to the terminal device, or the global cell identifier (CGI).

[0176] Exemplarily, the first network device includes cell a, cell b, and cell c. If the first network device sends the first identification information or the configuration information of the first model in cell b, then the first cell information may indicate cell b, such as the first cell information includes cell b.

[0177] Optionally, the first network device may send the first cell information to the second network device in a scenario where the terminal device undergoes a handover.

[0178] Note that the first network device may send the first identification information, the configuration information of the first model, the third indication information, and / or the first cell information to the second network device through one message, or the first network device may send the first identification information, the configuration information of the first model, the third indication information, and / or the first cell information to the second network device through multiple messages. The embodiments of the present application do not make any limitations in this regard.

[0179] The following Figure 2 shows the physical architecture of the access network device to further illustrate the specific implementation manner in which the first network device sends the configuration information of the first model, the third indication information, and / or the first cell information to the second network device.

[0180] Combined with Figure 2 , the first network device and the second network device may be Figure 2 the access network devices shown. Specifically, the DU of the first network device may send the configuration information of the first model, the third indication information, and / or the first cell information to the CU or CU-CP of the first network device through the F1-C interface. Then, the CU or CU-CP of the first network device sends the configuration information of the first model, the third indication information, and / or the first cell information to the CU or CU-CP of the second network device. The CU or CU-CP of the second network device sends the configuration information of the first model, the third indication information, and / or the first cell information to the DU of the second network device through the F1-C interface.

[0181] Alternatively, combined with Figure 2 , the first network device and the second network device may be Figure 2 the access network devices shown. Specifically, the CU or CU-CP of the first network device sends the configuration information of the first model, the third indication information, and / or the first cell information to the CU or CU-CP of the second network device.

[0182] When the access network device adopts a physical architecture different from Figure 2 that shown, the specific implementation manner in which the first network device sends the configuration information of the first model, the third indication information, and / or the first cell information to the second network device may be different.

[0183] Exemplarily, in addition to including Figure 2The CU and DU shown may further include an AIC. The first network device may be an access network device including the CU, DU, and AIC. Specifically, the AIC may be deployed above the CU, and the AIC of the first network device sends the configuration information of the first model, the third indication information, and / or the first cell information to the CU or CU-CP of the first network device. Then, the CU or CU-CP of the first network device sends the configuration information of the first model, the third indication information, and / or the first cell information to the CU or CU-CP of the second network device. The CU or CU-CP of the second network device sends the configuration information of the first model, the third indication information, and / or the first cell information to the AIC of the second network device.

[0184] When the first network device and the second network device are not access network devices, such as when the first network device and the second network device are AICs and the AIC does not belong to the access network device, the specific implementation of the first network device sending the configuration information of the first model, the third indication information, and / or the first cell information to the second network device is as follows.

[0185] Exemplarily, different from the AIC being deployed inside the access network device, the AIC may be a different network device from the access network device. Assume that the first network device is the first AIC and the second network device is the second AIC. The first AIC is located above the first access network device, and the second AIC is located above the second access network device. Specifically, the first AIC sends the configuration information of the first model and / or the second indication information to the first access network device. Then, the first access network device sends the configuration information of the first model and / or the second indication information to the second access network device. The second access network device sends the configuration information of the first model and / or the second indication information to the second AIC.

[0186] In a possible design, the first network device may send the first identification information or the configuration information of the first model to the core network element.

[0187] That is to say, the first network device may send the identification information corresponding to the configuration information of the model existing, inclined to, or recommended for use on the terminal device side to the core network element to indicate which model or models or the configuration information of the model exist, are inclined to, or are recommended for use in the terminal device. The first network device may send information such as the parameters of the first model, the algorithm of the first model, the hyperparameters of the first model, and / or the applicable scope of the first model to the core network element for the core network element to configure the configuration information of the first model for the second network device.

[0188] In a possible design, the first network device may send the third indication information to the core network element. Correspondingly, the core network element may receive the third indication information from the first network device.

[0189] Optionally, the third indication information may be used to indicate the applicable scope of the first model. At this time, the applicable scope of the first model may be indicated by both the configuration information of the first model and the third indication information, or indicated by the third indication information without using the configuration information of the first model.

[0190] That is to say, the first network device may separately send the applicable scope of the first model to the core network element through the third indication information.

[0191] In some embodiments, the first network device may send first cell information to the core network element. Correspondingly, the core network element may receive the first cell information from the first network device.

[0192] For the specific implementation manner of the first cell information, reference may be made to the above implementation manner, which will not be elaborated herein.

[0193] It should be noted that the first network device may send the first identification information, the configuration information of the first model, the third indication information, and / or the first cell information to the core network element through one message, or the first network device may send the first identification information, the configuration information of the first model, the third indication information, and / or the first cell information to the core network element through multiple messages. The embodiments of the present application do not make any limitations.

[0194] The following Figure 2 further describes the specific implementation manner of the first network device sending the first identification information, the configuration information of the first model, the third indication information, and / or the first cell information to the core network element in combination with the physical architecture of the access network device shown.

[0195] Combined with Figure 2 , the first network device may be Figure 2 the access network device shown. Specifically, the DU of the access network device may send the first identification information, the configuration information of the first model, the third indication information, and / or the first cell information to the CU or CU-CP of the access network device through the F1-C interface. Then, the CU or CU-CP of the access network device sends the first identification information, the configuration information of the first model, the third indication information, and / or the first cell information to the core network element.

[0196] Or, combined with Figure 2 , the first network device may be Figure 2 the access network device shown. Specifically, the CU or CU-CP of the access network device sends the first identification information, the configuration information of the first model, the third indication information, and / or the first cell information to the core network element.

[0197] When the access network device adopts a different Figure 2When the physical architecture shown is considered, the specific implementation manner in which the first network device sends the first identification information, the configuration information of the first model, the third indication information, and / or the first cell information to the core network element may be different.

[0198] Exemplarily, in the physical architecture of the access network device, in addition to including Figure 2 the shown CU and DU, it may further include an AIC. The first network device may be the access network device including the CU, DU, and AIC. Specifically, the AIC may be deployed above the CU, and the AIC of the access network device may send the first identification information, the configuration information of the first model, the third indication information, and / or the first cell information to the CU or CU-CP of the access network device. Then, the CU or CU-CP of the access network device sends the first identification information, the configuration information of the first model, the third indication information, and / or the first cell information to the core network element.

[0199] When the first network device is not an access network device, such as when the first network device is an AIC and the AIC does not belong to the access network device, the specific implementation manner in which the first network device sends the first identification information, the configuration information of the first model, the third indication information, and / or the first cell information to the core network element is as follows.

[0200] Exemplarily, different from the AIC being deployed inside the access network device, the AIC may be a different network device from the access network device. Specifically, the AIC sends the first identification information, the configuration information of the first model, the third indication information, and / or the first cell information to the access network device, and then the access network device sends the first identification information, the configuration information of the first model, the third indication information, and / or the first cell information to the core network element.

[0201] In some embodiments, in S401 above, the first network device sending the configuration information of the first model to the terminal device may include: the first network device sending at least one configuration information of the first model to the terminal device in a broadcast manner.

[0202] That is to say, the first network device may send at least one configuration information of the first model through a broadcast message, and each terminal device may receive at least one configuration information of the first model. By this method, the signaling overhead between the first network device and the terminal device can be saved.

[0203] Optionally, before the first network device sends the configuration information of the first model to the terminal device in S401 above, the communication method provided in the embodiments of the present application may further include: the first network device determines the configuration information of the first model.

[0204] Exemplarily, the first network device determines the configuration information of the first model, which may include: the first network device may generate identification information corresponding to the AI model and / or the ML model, and / or may determine which model(s) of the configuration information to configure for the terminal device.

[0205] Optionally, the terminal device may save the configuration information of the first model in one of its own variables. Further, the terminal device may also save one or more of the following in this variable of its own: the first identification information, the applicable scope of the first model, the valid time of the first model, and the first cell information.

[0206] S402, the terminal device obtains the first identification information.

[0207] In some embodiments, for S402 above, where the terminal device obtains the first identification information, it may include: the configuration information of the first model includes the first identification information, or the terminal device receives the first identification information from the first network device.

[0208] That is to say, the terminal device obtaining the first identification information may include: the terminal device receives the first identification information from the first network device. This first identification information may be generated by the first network device and sent to the terminal device.

[0209] In other embodiments, for S402 above, where the terminal device obtains the first identification information, it may include: the terminal device generates the first identification information. That is to say, the terminal device may assign or configure corresponding identification information for the models that already exist or are supported by itself. For example, after the terminal device receives the configuration information of the first model, the terminal device assigns or configures corresponding identification information for the configuration information of this first model. Another example is that before the terminal device receives the configuration information of the first model, the terminal device assigns corresponding identification information for various models supported by itself.

[0210] In a possible design, the terminal device may send the first identification information to the first network device. Correspondingly, the first network device may receive the first identification information from the terminal device.

[0211] That is to say, the terminal device may assign the first identification information to the first model that already exists or is supported by itself or the configuration of the first model, and send the first identification information to the first network device, so that the first network device knows the correspondence between the first model or the configuration of the first model and the first identification information.

[0212] Exemplarily, the terminal device may send capability information to the first network device, and the capability information may include the classification of the first model and the first identification information corresponding to the first model. The classification of the first model may refer to the name of the machine learning algorithm, or the function of the first model, or the name of the first model, etc.

[0213] Exemplarily, the terminal device may send the first identification information to the first network device through a MAC control element or an uplink physical control channel.

[0214] That is to say, if the first identification information is generated by the terminal device, the terminal device may send the first identification information to the first network device during the process of reporting capability information.

[0215] The following Figure 2 further describes the specific implementation manner of the above terminal device sending the first identification information to the first network device in combination with the physical architecture of the access network device shown.

[0216] In combination with Figure 2 , the first network device may be Figure 2 the access network device shown. The terminal device sends the first identification information to the CU or CU-CP of the access network device through the air interface. Then, the CU or CU-CP of the access network device sends the first identification information to the DU of the access network device through the F1-C interface.

[0217] Alternatively, the terminal device may send the first identification information to the DU of the access network device through a MAC control element or an uplink physical control channel.

[0218] When the access network device adopts a physical architecture different from Figure 2 that shown, the specific implementation manner of the above terminal device sending the first identification information to the first network device may be different.

[0219] Exemplarily, in addition to including Figure 2 the CU and DU shown, the physical architecture of the access network device may further include an AIC. The first network device may be the access network device including the CU, DU, and AIC. Specifically, the AIC may be deployed above the CU. The terminal device sends the first identification information to the CU or CU-CP of the access network device through the air interface. Then, the CU or CU-CP of the access network device sends the first identification information to the AIC of the access network device.

[0220] When the first network device is not an access network device, such as when the first network device is an AIC and the AIC does not belong to the access network device, the specific implementation manner of the above terminal device sending the first identification information to the first network device is as follows.

[0221] Exemplarily, different from the AIC being deployed inside the access network device, the AIC may be a different network device from the access network device. Specifically, the terminal device sends the first identification information to the access network device, and then the access network device sends the first identification information to the AIC, that is, the first network device.

[0222] In a possible design, the terminal device may send first identification information to a second network device.

[0223] Exemplarily, when the terminal device undergoes a handover, or moves from the idle state (RRC_idle) or the inactive state (RRC_inactive) to the connected state (RRC_connected), or when the terminal device undergoes an RRC re - establishment, the terminal device may send the first identification information to the second network device.

[0224] Specifically, a handover means that when the terminal device is in the connected state or the inactive state, it moves from cell 1 to cell 2. Cell 1 and cell 2 may be managed by different network devices or the same network device. In the embodiments of the present application, the terminal device moves from the first cell of the first network device to the second cell of the second network device.

[0225] The terminal device moving from the idle state or the inactive state to the connected state means that when the terminal device is in the idle state or the inactive state, after initiating an RRC establishment procedure or an RRC resume procedure in the resident cell, the network device managing the resident cell enables the terminal device to enter the connected state. In the embodiments of the present application, the network device managing the resident cell is the second network device.

[0226] The terminal device undergoing an RRC re - establishment means that when the terminal device is in the connected state, the terminal device detects a radio link failure, or detects an RRC establishment re - configuration failure, or experiences a handover failure. The terminal device triggers an RRC re - establishment procedure and will select a cell to initiate the RRC re - establishment. In the embodiments of the present application, the terminal device selects a cell of the second network device to initiate the RRC re - establishment.

[0227] It should be noted that in the embodiments of the present application, the first network device and the second network device may be the same network device, or the first network device and the second network device may be different network devices.

[0228] Optionally, the first identification information sent by the terminal device to the second network device may be generated by the terminal device itself or received by the terminal device from the first network device to indicate the model or the configuration information of the model that it currently has, or prefers or recommends using.

[0229] In some embodiments, before the terminal device sends the first identification information to the first network device or the second network device, the communication method provided by the embodiments of the present application may further include: the terminal device determines the first identification information.

[0230] That is to say, the terminal device determines a more preferred or recommended model or model configuration from the models it has, and sends the identification information corresponding to the more preferred or recommended model to the first network device or the second network device to request to use the model or model configuration information corresponding to the identification information.

[0231] Exemplarily, the terminal device may send the first identification information to the second network device through a MAC control element or an uplink physical control channel.

[0232] Taking the terminal device sending the first identification information to the second network device as an example below, the specific implementation manner for the terminal device to determine the first identification information is described.

[0233] In some embodiments, the communication method provided in the embodiments of the present application may include the following steps 1 to 2.

[0234] Step 1, the terminal device determines whether the public land mobile network list information applicable to the first model includes the registered public land mobile network (RPLMN) of the terminal device.

[0235] Exemplarily, the registered public land mobile network RPLMN is the public land mobile network PLMN registered by the terminal device before the last shutdown or network disconnection, or the terminal device has previously successfully performed the registration process of this PLMN with the core network.

[0236] For the specific implementation manner of the public land mobile network list information, reference may be made to S401 above, and details are not described herein again.

[0237] Step 2, if the public land mobile network list information applicable to the first model includes the registered public land mobile network of the terminal device, the terminal device sends the first identification information to the second network device.

[0238] Optionally, if the public land mobile network list information applicable to the first model does not include the registered public land mobile network of the terminal device, the terminal device may not send the first identification information to the second network device.

[0239] In some embodiments, the communication method provided in the embodiments of the present application may include the following steps 3 to 4.

[0240] Step 3, the terminal device determines whether at least one second identification information includes the first identification information, or determines whether the models corresponding to at least one second identification information include the first model corresponding to the first identification information.

[0241] Wherein, the second identification information may be used to indicate the models supported by the second network device or the configurations of the supported models, and the models are AI models or ML models.

[0242] Optionally, before the above step three, the communication method provided by the embodiments of the present application may further include: a second network device sending at least one second identification information to a terminal device. Correspondingly, the terminal device receives at least one second identification information from the second network device.

[0243] Exemplarily, the second network device may send the second identification information in a broadcast manner to reduce the signaling overhead between the network device and the terminal device.

[0244] Step four, if at least one second identification information includes the first identification information, or the model corresponding to at least one second identification information includes the first model corresponding to the first identification information, the terminal device sends the first identification information to the second network device.

[0245] Exemplarily, assume that at least one second identification information includes the identification information of model 1, the identification information of model 2, and the identification information of model 3, and the identification information corresponding to the models existing on the terminal device side includes the identification information of model 1, the identification information of model 2, and the identification information of model 4. Then the terminal device sends the identification information of model 1 and / or the identification information of model 2 to the second network device.

[0246] That is to say, the terminal device may send the identification information corresponding to the models supported by the second network device among the models existing on the terminal device side to the second network device, rather than sending the identification information corresponding to all the models existing on the terminal device side to the second network device, so that the second network device can quickly and accurately identify the model corresponding to the first identification information or the configuration of the model, and then quickly determine the model or the configuration information of the model that the terminal device can use.

[0247] Optionally, if at least one second identification information does not include the first identification information, or the model corresponding to at least one second identification information does not include the first model corresponding to the first identification information, the terminal device may not send the first identification information to the second network device.

[0248] In some embodiments, the communication method provided by the embodiments of the present application may include the following steps five to six.

[0249] Step five, the terminal device determines whether the first cell in the first network device is the same as the second cell in the second network device.

[0250] Among them, the first cell may be the cell in which the terminal device receives the first identification information, or the cell in which the terminal device receives the configuration information of the first model, or the terminal device uses the first model when the terminal device has a connection in the first cell. The second cell is the serving cell after the terminal device has switched, or after entering the connected state (RRC_connected) from the idle state (RRC_idle) or the inactive state (RRC_inactive), or after the terminal device has performed an RRC re-establishment. Alternatively, the second cell is the cell in which the terminal device sends the first identification information to the second network device.

[0251] That is to say, the terminal device receives the first identification information from the first network device in the first cell or uses the first model when the terminal device has a connection in the first cell, and then accesses the second network device in the second cell. The terminal device can determine whether the first cell is the same as the cell to which the terminal device is currently connected.

[0252] Step six, if the first cell in the first network device is the same as the second cell in the second network device, the terminal device sends the first identification information to the second network device.

[0253] That is to say, when the terminal enters the connected state from the idle state or the inactive state, or when a handover occurs, the terminal can send the identification information corresponding to the model that has been used in the current cell to the second network device, so that the second network device can quickly determine the model or the configuration information of the model that the terminal device can use, thereby improving the efficiency of the terminal to process data.

[0254] Optionally, if the first cell in the first network device is different from the second cell in the second network device, the terminal device may not send the first identification information to the second network device.

[0255] In some embodiments, the communication method provided by the embodiments of the present application may include the following steps seven to eight.

[0256] Step seven, the terminal device determines whether the cell list information includes the second cell.

[0257] For the specific implementation manner of the cell list information, reference may be made to S401 above, and details are not described herein again.

[0258] For the specific implementation manner of the second cell, reference may be made to step five above, and details are not described herein again.

[0259] Step eight, if the cell list information includes the second cell, the terminal device sends the first identification information to the second network device.

[0260] That is to say, if the applicable scope of the AI model or ML model includes the serving cell after the terminal device switches or enters the connected state, the terminal device sends the first identification information to the second network device, so that the second network device can quickly determine the model that the terminal device can use or the configuration information of the model.

[0261] Optionally, if the cell list information does not include the second cell, the terminal device may not send the first identification information to the second network device.

[0262] In some embodiments, the communication method provided by the embodiments of the present application may include the following steps nine to ten.

[0263] Step nine, the terminal device determines whether the first network device is the same as the second network device.

[0264] Step ten, if the first network device is the same as the second network device, the terminal device sends the first identification information to the second network device.

[0265] That is to say, when the first network device is the same as the second network device, the terminal device may have used the first model corresponding to the first identification information or the configuration information of the first model. When the model is needed again to process data, the configuration information of the model that already exists on the terminal device side can be requested, avoiding the terminal device from receiving the configuration parameters of the model again, thereby reducing the signaling overhead of the air interface.

[0266] Optionally, if the first network device is not the same as the second network device, the terminal device may not send the first identification information to the second network device.

[0267] In a possible design, the terminal device may send the first cell information to the second network device. Correspondingly, the second network device may receive the first cell information from the terminal device.

[0268] Optionally, the first cell information may be used to indicate the cell in which the terminal device receives the first identification information, and the first cell information may be used to indicate the cell in the first network device that sends the first identification information.

[0269] Exemplarily, the first network device includes Cell 1, Cell 2, and Cell 3. If the first network device sends the first identification information to the terminal device in Cell 2 and the terminal device receives the first identification information in Cell 2, the first cell information may be used to indicate Cell 2, for example, the first cell information may include Cell 2.

[0270] Optionally, the first cell information may be used to indicate that the terminal device used the first model when it had a connection with the first cell.

[0271] Exemplarily, the first network device includes cell 1, cell 2, and cell 3. If the terminal device is currently connected to cell 2 and is processing data using the configuration information of the first model, but the configuration information of the first model was obtained from cell 1 when the terminal device was connected to cell 1, then when the terminal device switches from cell 1 of the first network device to a cell of the second network device, the first cell information can be used to indicate cell 2. For example, the first cell information can include cell 2.

[0272] That is to say, the terminal device can send the first cell information to the second network device. When the second network device does not include the model or the configuration information of the model corresponding to the first identification information, the second network device can, based on the first cell information, learn the model or the configuration information of the model corresponding to the first identification information, and then determine whether the model or the configuration information of the model corresponding to the first identification information can be used by the terminal device.

[0273] Optionally, for the second network device to learn the model or the configuration information of the model corresponding to the first identification information based on the first cell information, it may include: the second network device can request the model or the configuration information of the model corresponding to the first identification information from the first network device based on the first cell information, or the first network device and the second network device will pre-interact with the models or the configuration information of the models they support and the corresponding identification information, and the second network device learns the model or the configuration information of the model corresponding to the first identification information based on the first cell information and the first identification information.

[0274] The following further describes the specific implementation manner of the above terminal device sending the first identification information and / or the first cell information to the second access network device in combination with Figure 2 the physical architecture of the access network device shown.

[0275] In combination with Figure 2 , the second network device can be Figure 2 the access network device shown. The terminal device sends the first identification information and / or the first cell information to the CU or CU-CP of the access network device through the air interface. Then, the CU or CU-CP of the access network device sends the first identification information and / or the first cell information to the DU of the access network device through the F1-C interface.

[0276] Alternatively, the terminal device can send the first identification information and / or the first cell information to the DU of the access network device through a MAC control element or an uplink physical control channel.

[0277] Or, in combination with Figure 2 , the second network device can be Figure 2 the access network device shown. Specifically, the terminal device sends the first identification information and / or the first cell information to the CU or CU-CP of the second network device through the air interface.

[0278] When the access network device adopts a physical architecture different from that Figure 2 shown, the specific implementation of the above terminal device sending the first identification information and / or the first cell information to the second network device may be different.

[0279] Exemplarily, in addition to the CU and DU included in the physical architecture of the access network device Figure 2 shown, an AIC may also be included. The second network device may be the access network device including the CU, DU, and AIC. Specifically, the AIC may be deployed above the CU, and the terminal device sends the first identification information and / or the first cell information to the CU or CU-CP of the access network device through the air interface. Then, the CU or CU-CP of the access network device sends the first identification information to the AIC of the access network device.

[0280] When the second network device is not an access network device, such as when the second network device is an AIC and the AIC does not belong to the access network device, the specific implementation of the above terminal device sending the first identification information and / or the first cell information to the second network device is as follows.

[0281] Exemplarily, different from the AIC being deployed inside the access network device, the AIC may be a different network device from the access network device. Specifically, the terminal device sends the first identification information and / or the first cell information to the access network device, and then the access network device sends the first identification information and / or the first cell information to the AIC, that is, the second network device.

[0282] In a possible design, the terminal device may send the first identification information or the configuration information of the first model to the core network element.

[0283] That is to say, the terminal device may send the identification information to the core network element to indicate which model(s)' configuration information exists in the terminal device, or may also send information such as the parameters of the first model, the algorithm of the first model, the hyperparameters of the first model, and / or the applicable scope of the first model to the core network element for the core network element to subsequently send the configuration information of the first model to the second network device.

[0284] Optionally, the terminal device may send the first identification information or the configuration information of the first model to the core network element through a non-access stratum (NAS) message.

[0285] In some embodiments, the terminal device may send the first cell information to the core network element. Correspondingly, the core network element may receive the first cell information from the terminal device.

[0286] That is to say, the terminal device can send the cell information for receiving the first identification information to the core network element, and configure the first cell information for the core network element as the second network device.

[0287] Optionally, the terminal device can send the first cell information to the core network element through a NAS message.

[0288] In some embodiments, the terminal device can send third indication information to the core network element. Correspondingly, the core network element can receive the third indication information from the terminal device.

[0289] For the specific implementation manner of the third indication information, reference can be made to S401 above, which will not be elaborated here.

[0290] That is to say, the terminal device can separately send the applicable range of the first model to the core network element through the third indication information.

[0291] In a possible design, the communication method provided by the embodiments of the present application may include: the core network element obtains the first identification information.

[0292] Optionally, the above-mentioned core network element obtaining the first identification information may include: the core network element receives the first identification information or the configuration information of the first model from the terminal device, or the core network element receives the first identification information or the configuration information of the first model from the first network device.

[0293] That is to say, the core network element can receive information such as the first identification information, the parameters of the first model, the algorithm of the first model, the hyperparameters of the first model, and / or the applicable range of the first model from the terminal device or the first network device.

[0294] In some embodiments, the core network element can send the first identification information or the configuration information of the first model to the second network device.

[0295] That is to say, the core network element can send information such as the first identification information, the parameters of the first model, the algorithm of the first model, the hyperparameters of the first model, and / or the applicable range of the first model to the second network device, so that the second network device can determine whether the model or the model configuration information existing on the terminal device side can be used by the terminal device, thereby saving the radio interface overhead between the terminal device and the network device.

[0296] Exemplarily, if the terminal device undergoes a handover, or enters the connected state from the idle state or the inactive state, the core network element can send information such as the first identification information, the parameters of the first model, the algorithm of the first model, the hyperparameters of the first model, and / or the applicable range of the first model to the second network device.

[0297] In some embodiments, the core network element may send third indication information to the second network device. Correspondingly, the second network device may receive the third indication information from the core network element.

[0298] For the specific implementation manner of the third indication information, reference may be made to S401 above, which will not be elaborated here.

[0299] That is to say, the first network device may send the applicable range of the first model to the core network element solely through the third indication information.

[0300] In some embodiments, the core network element may send first cell information to the second network device. Correspondingly, the second network device may receive the first cell information from the core network element.

[0301] For the specific implementation manner of the first cell information, reference may be made to the above implementation manner, which will not be elaborated here.

[0302] That is to say, the core network element may send the cell information of the terminal device receiving the first identification information to the second network device.

[0303] The following Figure 2 shows the physical architecture of the access network device, and further illustrates the specific implementation manner of the core network element sending the first identification information, the configuration information of the first model, the third indication information, and / or the first cell information to the second access network device.

[0304] Combined with Figure 2 , the second network device may be Figure 2 the access network device shown, and the DU of the access network device may use the first identification information, the configuration information of the first model, the third indication information, and / or the first cell information. Specifically, the core network element sends the first identification information, the configuration information of the first model, the third indication information, and / or the first cell information to the CU or CU-CP of the access network device. Then, the CU or CU-CP of the access network device sends the first identification information, the configuration information of the first model, the third indication information, and / or the first cell information to the DU of the access network device through the F1-C interface.

[0305] Or, combined with Figure 2 , the second network device may be Figure 2 the access network device shown, and the CU of the access network device may use the first identification information, the configuration information of the first model, the third indication information, and / or the first cell information. Specifically, the core network element sends the first identification information, the configuration information of the first model, the third indication information, and / or the first cell information to the CU or CU-CP of the access network device.

[0306] When the access network device adopts a different Figure 2When the physical architecture shown above is considered, the specific implementation methods for the above-mentioned core network element to send the first identification information, the configuration information of the first model, the third indication information, and / or the first cell information to the second network device may be different.

[0307] Exemplarily, in the physical architecture of the access network device, in addition to including Figure 2 the CU and DU shown above, it may also include an AIC. Optionally, the AIC can be deployed above the CU. The second network device can be the access network device including the CU, DU, and AIC. Specifically, the core network element sends the first identification information, the configuration information of the first model, the third indication information, and / or the first cell information to the CU or CU-CP of the access network device. Then, the CU or CU-CP of the access network device sends the first identification information, the configuration information of the first model, the third indication information, and / or the first cell information to the AIC of the access network device.

[0308] When the second network device is not an access network device, such as when the second network device is an AIC and the AIC does not belong to the access network device, the specific implementation method for the above-mentioned core network element to send the first identification information, the configuration information of the first model, the third indication information, and / or the first cell information to the second access network device is as follows.

[0309] Exemplarily, different from the AIC being deployed inside the access network device, the AIC can be a different network device from the access network device. Specifically, the core network element sends the first identification information, the configuration information of the first model, the third indication information, and / or the first cell information to the access network device, and then the access network device sends the first identification information, the configuration information of the first model, the third indication information, and / or the first cell information to the AIC, that is, the second network device.

[0310] Optionally, the terminal device can send the first identification information to the second network device or the core network element. The first identification information can be generated by the terminal device itself. The first identification information can be used to indicate the first model or the configuration information of the first model that the terminal device has, or the first identification information is the first cell information.

[0311] For example, if the second network device and the first network device have the same first model or the configuration information of the first model, the second network device can learn about the first model or the configuration information of the first model that the terminal device has based on the first identification information.

[0312] For another example, when the first network device and the second network device establish an interface (such as an Xn interface or an X2 interface) connection (i.e., before the terminal device sends the first identification information to the second network device or the core network element), they can exchange the configuration information and / or the first identification information of the first model supported by each other. Specifically, the following method can be adopted: The first network device sends an interface establishment request message to the second network device. Correspondingly, the second network device receives the interface establishment request message from the first network device. The second network device sends an interface establishment response message to the first network device. Correspondingly, the first network device receives the interface establishment response message from the second network device.

[0313] Exemplarily, the interface establishment request message may include the configuration information of at least one first model supported by the first network device and / or the first identification information corresponding to at least one first model supported by the first network device. Alternatively, the interface establishment request message may include the configuration information of at least one first model supported by each cell under the first network device and / or the first identification information corresponding to at least one first model supported by each cell under the first network device.

[0314] Exemplarily, the interface establishment response message may include the configuration information of at least one first model supported by the second network device and / or the first identification information corresponding to at least one first model supported by the second network device. Alternatively, the interface establishment response message may include the configuration information of at least one first model supported by each cell under the second network device and / or the first identification information corresponding to at least one first model supported by each cell under the second network device.

[0315] In this way, after the first network device and the second network device exchange the configuration information of the first model supported by each other, if the first network device supports the configuration information of one first model, or each cell under the first network device supports the configuration information of one first model, and the second network device supports the configuration information of one first model, or each cell under the second network device supports the configuration information of one first model, the second network device can obtain the first model or the configuration information of the first model possessed by the terminal device only according to the first cell information.

[0316] S403. The second network device obtains the first identification information.

[0317] In a possible design, the above S403, where the second network device obtains the first identification information, may include: The second network device receives the first identification information from the terminal device, or the second network device receives the first identification information and / or the configuration information of the first model from the first network device, or the second network device receives the first identification information and / or the configuration information of the first model from the core network element.

[0318] That is to say, the second network device can obtain information such as the first identification information, the parameters of the first model, the algorithm of the first model, the hyperparameters of the first model, and the applicable scope of the first model in various ways, such as receiving from the terminal device, the first network device, or the core network element.

[0319] It should be noted that the second network device can receive different information from the terminal device, the first network device, and the core network element respectively. For example, the second network device can receive the first identification information from the terminal device, receive the parameters of the first model, the hyperparameters of the first model, and the algorithm of the first model from the first network device, and receive the applicable scope of the first model from the core network element. Or, the first network device can receive the same information from the terminal device, the first network device, and the core network element. For example, the first network device can receive the first identification information from the terminal device, receive the first identification information, the parameters of the first model, the algorithm of the first model, and the hyperparameters of the first model from the first network device, and receive the first identification information, the parameters of the first model, the hyperparameters of the first model, and the algorithm of the first model from the core network element. Of course, the implementation manners for the second network device to obtain the first identification information and / or the configuration information of the first model may further include other examples, which are not enumerated one by one in this application.

[0320] When the second network device only receives the first identification information, if the model or the configuration information of the model existing on the first network device side is the same as the model or the configuration information of the model existing on the second network device side, the second network device can, according to the first identification information, learn the model or the configuration information of the model existing, preferred, or recommended on the terminal device side.

[0321] When the configuration information of the first model includes the first identification information and the applicable scope of the first model, even if the model existing on the first network device side is different from the model existing on the second network device side, the second network device can still, according to the configuration information of the first model, learn the model or the configuration information of the model existing, preferred, or recommended on the terminal device side.

[0322] When the configuration information of the first model includes the first identification information, the parameters of the first model, the hyperparameters of the first model, and the algorithm of the first model, it can not only indicate the model or the configuration information of the model existing, preferred, or recommended in the terminal device, but also interact the corresponding relationship between the model or the configuration of the model and the identification of the model between the first network device and the second network device.

[0323] When the configuration information of the first model includes the first identification information, the parameters of the first model, the hyperparameters of the first model, the algorithm of the first model, and the applicable scope of the first model, it can not only indicate the model or the configuration information of the model that exists, tends to, or is recommended in the terminal device, but also further interact the correspondence relationship between the model or the configuration of the model and the identification of the model between the first network device and the second network device.

[0324] When the second network device receives the first identification information and the first cell information from the terminal device, the second network device can obtain the configuration information of the first model supported by the first network device, or the configuration information of at least one first model supported by each cell under the first network device according to the first cell information, and obtain the corresponding configuration information of the first model according to the first identification information, so as to know the model or the configuration information of the model that exists, tends to, or is recommended in the terminal device.

[0325] S404, the second network device sends the first indication information to the terminal device. Correspondingly, the terminal device receives the first indication information from the second network device.

[0326] Wherein, the first indication information is used to indicate that the terminal device adopts the configuration information of the first model corresponding to the first identification information.

[0327] Exemplarily, the first indication information may include the first identification information or a boolean variable. The boolean variable can indicate whether to adopt the configuration information of the first model that already exists on the terminal device side. If the first indication information includes the first identification information, it can indicate which model or models or the configuration information of the model the terminal device adopts.

[0328] In some embodiments, the above S404, where the second network device sends the first indication information to the terminal device, may include the following steps eleven to fourteen.

[0329] Step eleven, the second network device determines at least one third identification information.

[0330] Wherein, the third identification information can be used to indicate the first model or the configuration information of the first model available to the terminal device in the second network device.

[0331] That is to say, the second network device determines the model or the configuration information of the model that the terminal device can use. Specifically, the second network device can directly determine the model or the configuration information of the model that the terminal device can use from the received first identification information, or can use other methods to determine, which is not specifically limited in this application.

[0332] Step twelve, the second network device determines whether at least one third identification information includes the first identification information.

[0333] In some embodiments, if at least one piece of third identification information includes the first identification information, the second network device performs step thirteen below.

[0334] Exemplarily, assume that at least one piece of third identification information includes the identification information corresponding to model 4, the identification information corresponding to model 5, and the identification information corresponding to model 6, and the first identification information includes multiple pieces of identification information. For example, if the first identification information includes the identification information corresponding to model 4 and the identification information corresponding to model 5, it can be determined that at least one piece of third identification information includes the first identification information.

[0335] Exemplarily, assume that at least one piece of third identification information includes the identification information corresponding to model 4, the identification information corresponding to model 5, and the identification information corresponding to model 6, and the first identification information includes multiple pieces of identification information. For example, if the first identification information includes the identification information corresponding to model 4 and the identification information corresponding to model 7, it can be determined that at least one piece of third identification information includes the first identification information.

[0336] That is to say, if at least one piece of third identification information includes all of the first identification information, or if at least one piece of third identification information includes some of the first identification information, it can be determined that at least one piece of third identification information includes the first identification information.

[0337] In some embodiments, if at least one piece of third identification information does not include the first identification information, the second network device performs step fourteen below.

[0338] Exemplarily, assume that at least one piece of third identification information includes the identification information corresponding to model 4, the identification information corresponding to model 5, and the identification information corresponding to model 6, and the first identification information includes multiple pieces of identification information. For example, if the first identification information includes the identification information corresponding to model 7 and the identification information corresponding to model 8, then at least one piece of third identification information does not include the first identification information.

[0339] That is to say, when at least one piece of third identification information does not include all of the first identification information, that is, when there is no intersection between at least one piece of third identification information and the first identification information, it can be determined that at least one piece of third identification information does not include the first identification information.

[0340] Step thirteen: The second network device sends first indication information to the terminal device.

[0341] Exemplarily, assume that at least one piece of third identification information includes the identification information corresponding to model 4, the identification information corresponding to model 5, and the identification information corresponding to model 6, and the first identification information includes multiple pieces of identification information. For example, if the first identification information includes the identification information corresponding to model 4 and the identification information corresponding to model 5, it can indicate that the terminal device adopts the identification information corresponding to model 4 and / or the identification information corresponding to model 5.

[0342] Exemplarily, assume that at least one third identification information includes identification information corresponding to model 4, identification information corresponding to model 5, and identification information corresponding to model 6, and the first identification information includes multiple pieces of identification information. For example, if the first identification information includes identification information corresponding to model 4 and identification information corresponding to model 7, then the terminal device can be instructed to adopt the identification information corresponding to model 4.

[0343] That is to say, when the first identification information includes multiple pieces of identification information, the second network device can send all or part of the identification information in the first identification information to the terminal device to instruct the terminal device to adopt which model(s) or configuration information of the model.

[0344] Step Fourteen, the second network device sends the configuration information of at least one first model corresponding to at least one third identification information to the terminal device.

[0345] Exemplarily, assume that at least one third identification information includes identification information corresponding to model 4, identification information corresponding to model 5, and identification information corresponding to model 6, and the first identification information includes multiple pieces of identification information. For example, if the first identification information includes identification information corresponding to model 7 and identification information corresponding to model 8, then the configuration information corresponding to model 4 and / or model 5 and / or model 6, such as corresponding identification information, parameters, hyperparameters, applicable scope, and / or valid time, etc., is sent to the terminal device to achieve network intelligence.

[0346] In some embodiments, the above S404, where the second network device sends the first indication information to the terminal device, may include the following steps Fifteen to Seventeen.

[0347] Step Fifteen, the second network device determines whether the second network device supports the configuration information of the first model corresponding to the first identification information.

[0348] If the second network device supports the configuration information of the first model corresponding to the first identification information, the second network device executes the following Step Sixteen; otherwise, the second network device executes the following Step Seventeen.

[0349] Step Sixteen, the second network device sends the first indication information to the terminal device.

[0350] Exemplarily, assume that the second network device supports the identification information corresponding to model 4, the identification information corresponding to model 5, and the identification information corresponding to model 6, and the first identification information includes multiple pieces of identification information. For example, if the first identification information includes the identification information corresponding to model 4 and the identification information corresponding to model 5, then the terminal device can be instructed to adopt the identification information corresponding to model 4 and / or the identification information corresponding to model 5.

[0351] Step Seventeen, the second network device sends the configuration information of at least one model supported by the second network device or the model to the terminal device.

[0352] Exemplarily, assume that the second network device supports the identification information corresponding to Model 4, the identification information corresponding to Model 5, and the identification information corresponding to Model 6. The first identification information includes multiple pieces of identification information. For example, the first identification information includes the identification information corresponding to Model 7 and the identification information corresponding to Model 8. Then, send the configuration information corresponding to Model 4 and / or Model 5 and / or Model 6 to the terminal device, such as the corresponding identification information, parameters, hyperparameters, applicable scope, and / or valid time, etc., to achieve network intelligence.

[0353] It should be noted that S404 is optional, that is, the second network device may not need to send the first indication information to the terminal device, and the second network device and the terminal device default to use the configuration information of the first model that the terminal device already has.

[0354] S405, the terminal device processes data using the configuration information of the first model.

[0355] Exemplarily, the configuration information of the first model adopted by the terminal device may include the parameters of the first model, the hyperparameters of the first model, the algorithm of the first model, and may also include one or more of the hyperparameters of the first model, the applicable scope of the first model, the valid time of the first model, and the identification information of the first model.

[0356] In some embodiments, the above S405, where the terminal device processes data using the configuration information of the first model, may include: the terminal device performs training using the configuration information of the first model.

[0357] Exemplarily, training refers to a processing process in which an AI model or an ML model learns to perform a specific task. Generally, by optimizing the weights in the AI model or the ML model, the AI model or the ML model learns to perform a specific task. Training methods may include: supervised learning, unsupervised learning, reinforcement learning, and / or transfer learning, etc.

[0358] Among them, supervised learning is to use a set of training samples that have been correctly labeled for training. Being correctly labeled means that for each training sample, an expected output value is provided.

[0359] Unsupervised learning refers to a method in which no pre-labeled training samples are given, the provided training samples are unlabeled, and the algorithm is required to automatically classify or cluster the input training samples.

[0360] Reinforcement learning is a field in machine learning that emphasizes how to act based on the environment to achieve the maximum expected benefit, that is, the algorithm interacts with the dynamic environment, takes the feedback of the environment as input, and through learning, selects the optimal actions that can achieve its goals. The inspiration for reinforcement learning comes from the behavioral theory in psychology, that is, how organisms gradually form expectations of stimuli under the stimulation of rewards or punishments given by the environment, and produce habitual behaviors that can obtain the greatest benefits.

[0361] Transfer learning is a research area belonging to machine learning. It focuses on storing the solution models of existing problems and applying them to other different but related problems. For example, the knowledge (or model) used to identify cars can also be used to improve the ability to identify trucks.

[0362] In some other embodiments, for the above S405, the terminal device processes data using the configuration information of the first model, which may include: the terminal device performs inference using the configuration information of the first model.

[0363] Exemplarily, inference means that after training, the trained AI model or ML model is used to perform tasks, and the input samples are processed by the AI model or ML model to obtain corresponding prediction results.

[0364] Optionally, the second network device can also process data using the configuration information of the new first model. The method for the second network device to process data is similar to that of the terminal device to process data, and will not be elaborated here.

[0365] In a possible design, the second network device can send the first identification information corresponding to the configuration information of the new first model to the terminal device. Correspondingly, the terminal device receives the first identification information corresponding to the configuration information of the new first model from the second network device.

[0366] Among them, the configuration information of the new first model is different from the configuration information of the first model used by the terminal device last time, or the configuration information of the new first model is different from the configuration information of the first model indicated by the first indication information.

[0367] Exemplarily, in step S404, the first indication information indicates that the terminal device uses the configuration information of model 1, and the configuration information of the new first model is the configuration information of model 2.

[0368] That is to say, the second network device can change the configuration information of the first model used by the terminal device. When changing, sending the first indication information can further save the signaling overhead of the air interface or can quickly change the first model.

[0369] Optionally, the second network device may carry the first identification information corresponding to the configuration information of the new first model through an RRC message, a MAC layer control element, or a downlink physical control channel.

[0370] In another possible design, the terminal device may send the first identification information corresponding to the configuration information of the new first model to the second network device. Correspondingly, the second network device receives the first identification information corresponding to the configuration information of the first model from the terminal device.

[0371] That is to say, the terminal device may request the second network device to switch the configuration information of the first model, and send the first indication information during the change, which can further save the signaling overhead of the air interface or can quickly change the first model.

[0372] Optionally, the terminal device may carry the first identification information corresponding to the configuration information of the new first model through an RRC message, a MAC layer control element, or an uplink physical control channel.

[0373] In some embodiments, the terminal device may process data using the configuration information of the new first model.

[0374] Exemplarily, the terminal device may switch from processing data using the configuration information of Model 1 to processing data using the configuration information of Model 2.

[0375] Based on Figure 4 the communication method shown, the terminal device obtains the first identification information corresponding to the configuration of the first model that already exists in itself, the second network device obtains the first identification information, and sends the first indication information to the terminal device to instruct the terminal device to use the AI model or ML model that already exists in itself, which can avoid the second network device from sending the configuration parameters of the first model to the terminal device, thereby saving the signaling overhead of the air interface.

[0376] Figure 5 For the communication method provided in the embodiments of the present application, the process is schematically shown Figure 2 . This communication method can be applicable to Figure 1 the communication between the terminal device, the first network device, and the second network device shown.

[0377] As Figure 5 shown, this communication method includes the following steps:

[0378] S501, the first network device sends the configuration information of the first model to the terminal device. Correspondingly, the terminal device receives the configuration information of the first model from the first network device.

[0379] For the specific implementation manner of S501, reference may be made to S401 above, and details are not described herein again.

[0380] For the specific implementation of the configuration information of the first model, reference may be made to S401 above, which will not be elaborated here.

[0381] In a possible design, the first network device may send second indication information to the terminal device. Correspondingly, the terminal device may receive the second indication information from the first network device. For the specific implementation, reference may be made to the corresponding implementation in S401 above, which will not be elaborated here.

[0382] In a possible design, before the terminal device receives the configuration information of the first model from the first network device in S501 above, the communication method provided by the embodiments of the present application may further include: the terminal device may send first identification information to the first network device. Correspondingly, the first network device may receive the first identification information from the terminal device. For the specific implementation, reference may be made to the corresponding implementation in S402 above, which will not be elaborated here.

[0383] That is to say, the terminal device may assign first identification information to the existing first model or the configuration of the first model for itself, and send the first identification information to the first network device, so that the first network device can learn the correspondence between the first model or the configuration of the first model and the first identification information.

[0384] S502. The terminal device sends the first identification information to the second network device. Correspondingly, the second network device receives the first identification information from the terminal device.

[0385] For S502, for the specific implementation of the terminal device sending the first identification information to the second network device, reference may be made to the corresponding implementation in S402 above, which will not be elaborated here.

[0386] For S502, for the specific implementation of the second network device receiving the first identification information from the terminal device, reference may be made to the corresponding implementation in S403 above, which will not be elaborated here.

[0387] In some embodiments, the terminal device may obtain the first identification information. For the specific implementation, reference may be made to S402 above, which will not be elaborated here.

[0388] In a possible design, the terminal device may send first cell information to the second network device. Correspondingly, the second network device may receive the first cell information from the terminal device. For the specific implementation, reference may be made to the corresponding implementation in S402 above, which will not be elaborated here.

[0389] S503. The second network device sends the first indication information to the terminal device. Correspondingly, the terminal device receives the first indication information from the second network device.

[0390] For the specific implementation of S503, reference may be made to the above S404, which will not be elaborated here.

[0391] S504, the terminal device processes data using the configuration information of the first model.

[0392] For the specific implementation of S504, reference may be made to the above S405, which will not be elaborated here.

[0393] Based on Figure 5 the communication method shown, the terminal device obtains the first identification information corresponding to the model already existing in itself, and sends the first identification information to the second network device, so that the second network device sends the first indication information to the terminal device according to the first identification information, instructing the terminal device to process data using the model already existing in itself, which can avoid the second network device from sending the configuration parameters of the first model to the terminal device, thereby saving the signaling overhead of the air interface.

[0394] Figure 6 is a schematic flow of the communication method provided by the embodiments of this application Figure 3 . This communication method can be applicable to Figure 1 the communication among the terminal device, the first network device and the second network device shown.

[0395] As Figure 6 shown, this communication method includes the following steps:

[0396] S601, the first network device sends the configuration information of the first model to the terminal device. Correspondingly, the terminal device receives the configuration information of the first model from the first network device.

[0397] For the specific implementation of S601, reference may be made to the above S501, which will not be elaborated here.

[0398] S602, the first network device sends the first identification information to the second network device. Correspondingly, the second network device receives the first identification information from the first network device.

[0399] For S602, the specific implementation of the first network device sending the first identification information to the second network device, reference may be made to the corresponding implementation in the above S401, which will not be elaborated here.

[0400] For S602, the specific implementation of the second network device receiving the first identification information from the first network device, reference may be made to the corresponding implementation in the above S403, which will not be elaborated here.

[0401] In a possible design, the first network device may send the configuration information of the first model to the second network device. Correspondingly, the second network device receives the configuration information of the first model from the first network device. The specific implementation manner may refer to the corresponding implementation manners in S401 and S403 above, and will not be elaborated here.

[0402] In a possible design, the first network device may send third indication information to the second network device. Correspondingly, the second network device may receive the third indication information from the first network device. The specific implementation manner may refer to the corresponding implementation manner in S401 above, and will not be elaborated here.

[0403] In a possible design, the first network device may send first cell information to the second network device. Correspondingly, the second network device may receive the first cell information from the first network device. The specific implementation manner may refer to the corresponding implementation manner in S401 above, and will not be elaborated here.

[0404] S603. The second network device sends first indication information to the terminal device. Correspondingly, the terminal device receives the first indication information from the second network device.

[0405] For the specific implementation manner of S603, reference may be made to S404 above, and will not be elaborated here.

[0406] S604. The terminal device processes data using the configuration information of the first model.

[0407] For the specific implementation manner of S604, reference may be made to S405 above, and will not be elaborated here.

[0408] Based on Figure 6 the communication method shown, the first network device sends the first identification information corresponding to the first model already existing on the terminal device side to the second network device, so that the second network device sends first indication information to the terminal device according to the first identification information, instructing the terminal device to process data using the first model already existing on its own, which can avoid the second network device from sending the configuration of the first model to the terminal device, thereby saving the signaling overhead of the air interface.

[0409] Figure 7 It is a schematic flow of the communication method provided by the embodiment of the present application Figure 4 . This communication method can be applicable to Figure 1 the communication between any two nodes shown.

[0410] As Figure 7 shown, this communication method includes the following steps:

[0411] S701, the first network device sends the configuration information of the first model to the terminal device. Correspondingly, the terminal device receives the configuration information of the first model from the first network device.

[0412] For the specific implementation of S701, reference may be made to S501 above, which will not be elaborated here.

[0413] S702, the first network device sends the first identification information to the core network element. Correspondingly, the core network element receives the first identification information from the first network device.

[0414] Regarding S702, for the specific implementation of the first network device sending the first identification information to the core network element, reference may be made to the corresponding implementation in S401 above, which will not be elaborated here.

[0415] Regarding S702, for the specific implementation of the core network element receiving the first identification information from the first network device, reference may be made to the corresponding implementation in S402 above, which will not be elaborated here.

[0416] In a possible design, the first network device may send the configuration information of the first model to the core network element. Correspondingly, the core network element receives the configuration information of the first model from the first network device. For the specific implementation, reference may be made to the corresponding implementation in S401 and S402 above, which will not be elaborated here.

[0417] In a possible design, the first network device may send the third indication information to the core network element. Correspondingly, the core network element may receive the third indication information from the first network device. For the specific implementation, reference may be made to the corresponding implementation in S401 above, which will not be elaborated here.

[0418] In a possible design, the first network device may send the first cell information to the core network element. Correspondingly, the core network element may receive the first cell information from the first network device. For the specific implementation, reference may be made to the corresponding implementation in S401 above, which will not be elaborated here.

[0419] S703, the terminal device sends the first identification information to the core network element. Correspondingly, the core network element receives the first identification information from the terminal device.

[0420] It should be noted that Figure 7 The communication method shown may include S701, S702, S704, and S705, or include S701, S703 - S705. The core network element may receive the first identification information from the first network device or the terminal device. Correspondingly, the first network device may send the first indication information to the core network element, or the terminal device may send the first indication information to the core network element.

[0421] For the specific implementation method of S703, reference can be made to the corresponding implementation method in S402 above, which will not be elaborated here.

[0422] In a possible design solution, the terminal device can send the configuration information of the first model to the core network element. Correspondingly, the core network element can receive the configuration information of the first model from the terminal device. For the specific implementation method, reference can be made to the corresponding implementation method in S402 above, which will not be elaborated here.

[0423] In a possible design solution, the terminal device can send the first cell information to the core network element. Correspondingly, the core network element can receive the first cell information from the terminal device. For the specific implementation method, reference can be made to the corresponding implementation method in S402 above, which will not be elaborated here.

[0424] In a possible design solution, the terminal device can send the third indication information to the core network element. Correspondingly, the core network element can receive the third indication information from the terminal device. For the specific implementation method, reference can be made to the corresponding implementation method in S402 above, which will not be elaborated here.

[0425] S704, the core network element sends the first identification information to the second network device. Correspondingly, the second network device receives the first identification information from the core network element.

[0426] Regarding S704, for the specific implementation method of the core network element sending the first identification information to the second network device, reference can be made to the corresponding implementation method in S402 above, which will not be elaborated here.

[0427] Regarding S704, for the specific implementation method of the second network device receiving the first identification information from the core network element, reference can be made to the corresponding implementation method in S403 above, which will not be elaborated here.

[0428] In a possible design solution, the core network element can send the configuration information of the first model to the second network device. Correspondingly, the second network device can receive the configuration information of the first model from the core network element. For the specific implementation method, reference can be made to the corresponding implementation methods in S402 and S403 above, which will not be elaborated here.

[0429] In a possible design solution, the core network element can send the third indication information to the second network device. Correspondingly, the second network device can receive the third indication information from the core network element. For the specific implementation method, reference can be made to the corresponding implementation method in S402 above, which will not be elaborated here.

[0430] In a possible design, the core network element may send first cell information to the second network device. Correspondingly, the second network device may receive the first cell information from the core network element. The specific implementation may refer to the corresponding implementation in S402 above and will not be elaborated here.

[0431] S705. The second network device sends first indication information to the terminal device. Correspondingly, the terminal device receives the first indication information from the second network device.

[0432] Regarding the specific implementation of S705, reference may be made to S404 above and will not be elaborated here.

[0433] S706. The terminal device processes data using the configuration information of the first model.

[0434] Regarding the specific implementation of S706, reference may be made to S405 above and will not be elaborated here.

[0435] Based on Figure 7 the communication method shown, the core network element obtains the first identification information corresponding to the first model already existing on the terminal device side from the terminal device or the first network device, and sends it to the second network device, so that the second network device sends first indication information to the terminal device according to the first identification information, instructing the terminal device to process data using the first model already existing on its own, which can avoid the second network device sending the configuration of the first model to the terminal device, thereby saving signaling overhead on the air interface.

[0436] Figure 8 is a schematic flow of the communication method provided by the embodiments of the present application Figure 5 . This communication method can be applied to Figure 1 the communication between the terminal device and the first network device, or between the terminal device and the second network device shown.

[0437] As Figure 8 shown, this communication method includes the following steps:

[0438] S801. The first network device sends the configuration information of at least one first model to the terminal device by broadcasting. Correspondingly, the terminal device receives the configuration information of at least one first model from the first network device.

[0439] Regarding the specific implementation of the configuration information of the first model, reference may be made to S401 above and will not be elaborated here.

[0440] Regarding the specific implementation of S801, reference may be made to S401 above and will not be elaborated here.

[0441] It should be noted that Figure 8The first network device in the communication method shown may be the second network device, and is not limited to the first network device.

[0442] S802. The terminal device sends first identification information to the first network device. Correspondingly, the first network device receives the first identification information from the terminal device.

[0443] Regarding the specific implementation manner of S802, which is similar to that of S502 above, where the terminal device sends first identification information to the second network device. Correspondingly, the second network device receives the first identification information from the terminal device. The specific implementation manner can refer to S502 above and will not be elaborated here.

[0444] Optionally, S802 is an optional step.

[0445] S803. The first network device sends first indication information to the terminal device. Correspondingly, the terminal device receives the first indication information from the first network device.

[0446] Regarding the specific implementation manner of S803, which is similar to that of S404 above, where the second network device sends first indication information to the terminal device. Correspondingly, the terminal device receives the first indication information from the second network device. The specific implementation manner can refer to S404 above and will not be elaborated here.

[0447] Optionally, S803 is an optional step. For example, Figure 8 The communication method shown includes step S801 and step S802. The first network device and the terminal device default to use the configuration information of the first model corresponding to the first identification information in step S802.

[0448] Optionally, the first network device may send the first identification information to the terminal device by unicast (or a dedicated message), so that the terminal device obtains the configuration information of the first model according to the first identification information in the dedicated message.

[0449] S804. The terminal device processes data using the configuration information of the first model.

[0450] Regarding the specific implementation manner of S804, it can refer to S405 above and will not be elaborated here.

[0451] Optionally, the first network device may also process data using the configuration information of the new first model.

[0452] S805. The first network device may send the first identification information corresponding to the configuration information of the new first model to the terminal device. Correspondingly, the terminal device receives the first identification information corresponding to the configuration information of the new first model from the first network device.

[0453] Among them, the configuration information of the new first model is different from the configuration information of the first model adopted by the terminal device last time, or the configuration information of the new first model is different from the configuration information of the first model indicated by the first indication information.

[0454] Exemplarily, it is assumed that in step S803, the first indication information indicates that the terminal device adopts the configuration information of model 1, and in step S805, the configuration information of the new first model is the configuration information of model 2.

[0455] That is to say, the first network device can change the configuration information of the first model adopted by the terminal device. When changing, the first identification information is sent, which can further save the signaling overhead of the air interface or can quickly change the first model.

[0456] The configuration information of the new first model is carried in S801.

[0457] Optionally, the first network device can carry the first identification information corresponding to the configuration information of the new first model through an RRC message or a MAC layer control element or a downlink physical control channel.

[0458] S806, the terminal device sends the first identification information corresponding to the configuration information of the new first model to the first network device. Correspondingly, the first network device receives the first identification information corresponding to the configuration information of the first model from the terminal device.

[0459] Among them, the configuration information of the new first model is different from the configuration information of the first model adopted by the terminal device last time, or the configuration information of the new first model is different from the configuration information of the first model indicated by the first indication information.

[0460] Exemplarily, it is assumed that in step S803, the first indication information indicates that the terminal device adopts the configuration information of model 1, and in step S806, the configuration information of the new first model is the configuration information of model 2.

[0461] That is to say, the terminal device can request the first network device to switch the configuration information of the first model. When changing, the first identification information is sent, which can further save the signaling overhead of the air interface or can quickly change the first model.

[0462] Optionally, the terminal device can carry the first identification information corresponding to the configuration information of the new first model through an RRC message or a MAC layer control element or a physical channel.

[0463] The configuration information of the new first model is carried in S801.

[0464] Optionally, after S806, the terminal receives the first indication information from the first network device.

[0465] It should be noted that Figure 8 The communication method shown may include S801 - S805 and S807, or may include S801 - S804, S806 - S807. S805 and S806 can be parallel steps, and the change of the first model can be triggered by the first network device or the terminal device.

[0466] S807, the terminal device processes data using the configuration information of the new first model.

[0467] Optionally, the first network device can also process data using the configuration information of the new first model.

[0468] It should be noted that S805 - S807 can be optional steps.

[0469] Based on Figure 8 The communication method shown, the network device sends the configuration information of at least one first model through a broadcast message, and each terminal device can receive the configuration information of at least one first model. Through this method, the signaling overhead between the network device and the terminal device can be saved. The terminal device sends the first identification information corresponding to the first model it prefers or recommends to use to the network device, and the network device sends the first indication information to the terminal device, instructing the terminal device to process data using the model that already exists in itself, which can avoid the network device from frequently sending the configuration parameters of the first model to the terminal device and can further save the signaling overhead of the air interface. And the network device and the terminal device can trigger the change of the first model, and send the first identification information when changing, which can further save the signaling overhead of the air interface or can quickly change the first model.

[0470] Figure 9 It is a schematic flow of the communication method provided by the embodiments of this application Figure 6 . This communication method can be applicable to Figure 1 the communication between the terminal device shown and the first network device, or between the terminal device and the second network device.

[0471] As Figure 9 shown, this communication method includes the following steps:

[0472] S901, the first network device sends the configuration information of at least one first model to the terminal device through unicast (or a dedicated RRC message). Correspondingly, the terminal device receives the configuration information of at least one first model from the first network device.

[0473] For the specific implementation manner of the configuration information of the first model, reference can be made to the above S401, which will not be elaborated here.

[0474] For the specific implementation manner of S901, reference can be made to the above S401, which will not be elaborated here.

[0475] It should be noted that Figure 9 the first network device in the communication method shown can be the second network device, not limited to the first network device.

[0476] S902. The terminal device sends the first identification information to the first network device. Correspondingly, the first network device receives the first identification information from the terminal device.

[0477] For the specific implementation manner of S902, reference can be made to the above S802, which will not be elaborated here.

[0478] S903. The first network device sends the first indication information to the terminal device. Correspondingly, the terminal device receives the first indication information from the first network device.

[0479] For the specific implementation manner of S903, reference can be made to the above S803, which will not be elaborated here.

[0480] S904. The terminal device processes data using the configuration information of the first model.

[0481] For the specific implementation manner of S904, reference can be made to the above S405, which will not be elaborated here.

[0482] S905. The first network device can send the first identification information corresponding to the configuration information of the new first model to the terminal device. Correspondingly, the terminal device receives the first identification information corresponding to the configuration information of the new first model from the first network device.

[0483] For the specific implementation manner of S905, reference can be made to the above S805, which will not be elaborated here.

[0484] Among them, the configuration information of the new first model is carried in S901.

[0485] S906. The terminal device sends the first identification information corresponding to the configuration information of the new first model to the first network device. Correspondingly, the first network device receives the first identification information corresponding to the configuration information of the first model from the terminal device.

[0486] For the specific implementation manner of S906, reference can be made to the above S806, which will not be elaborated here.

[0487] Among them, the configuration information of the new first model is carried in S901.

[0488] It should be noted that Figure 9The communication method shown may include S901 - S905 and S907, or may include S901 - S904, S906 - S907. That is to say, S905 and S906 may be parallel steps, and the change of the first model may be triggered by the first network device or the terminal device.

[0489] S907, the terminal device processes data using the configuration information of the new first model.

[0490] It should be noted that S905 - S907 may be optional steps.

[0491] Based on Figure 9 the communication method shown, the network device sends the configuration information of at least one first model by unicast or a dedicated RRC message. Each terminal device can receive the configuration information of at least one first model. The network device and the terminal device can trigger the change of the first model. When changing, the first identification information is sent, which can further save the signaling overhead of the air interface or can quickly change the first model.

[0492] Combined with Figures 3 - 9 the above, the communication method provided by the embodiments of the present application is described in detail. Next, combined with Figure 10 Figure 13 the communication device provided by the embodiments of the present application is described in detail.

[0493] Figure 10 is a schematic structural diagram of the communication device provided by the embodiments of the present application Figure 2 . This communication device is applicable to Figure 1 the communication system shown, and executes Figures 4 - 9 the functions of the terminal device in the communication method shown. For the sake of convenience of description, Figure 10 only the main components of this communication device are shown.

[0494] As Figure 10 shown, the communication device 1000 includes: a transceiver module 1001 and a processing module 1002.

[0495] The transceiver module 1001 is used to receive the configuration information of the first model from the first network device. Among them, the first model is an artificial intelligence (AI) model or a machine learning (ML) model.

[0496] The processing module 1002 is used to obtain the first identification information. Among them, the first identification information is used to identify the configuration of the first model.

[0497] The transceiver module 1001 is further used to receive the first indication information from the second network device. Among them, the first indication information is used to indicate to use the configuration information of the first model corresponding to the first identification information.

[0498] The processing module 1002 is further configured to process data by using the configuration information of the first model.

[0499] In a possible design, the configuration information of the first model may include first identification information.

[0500] In a possible design, the processing module 1002 is further configured to generate the first identification information.

[0501] In a possible design, the first identification information may include one or more of the following: an identification of the configuration information of the first model, a name of the first model, and a function of the first model.

[0502] In a possible design, the configuration information of the first model may include parameters of the first model, hyperparameters of the first model, and / or an algorithm of the first model.

[0503] In a possible design, the transceiver module 1001 is further configured to receive second indication information from a first network device. The second indication information may be used to indicate a scope of application of the first model and / or a valid time of the first model.

[0504] Optionally, the scope of application of the first model may include list information of applicable public land mobile networks and / or list information of applicable cells.

[0505] Optionally, the list information of public land mobile networks may include a registered public land mobile network of the terminal device.

[0506] Optionally, the first network device may be the same as the second network device.

[0507] Optionally, a first cell in the first network device may be the same as a second cell in the second network device. The first cell is a cell in which the first identification information is received, and the second cell is a cell in which the first identification information is sent.

[0508] Optionally, the list information of cells may include the second cell.

[0509] In a possible design, the transceiver module 1001 is further configured to send the first identification information to a second network device.

[0510] In a possible design, the transceiver module 1001 is further configured to receive at least one second identification information from the second network device. The second identification information may be used to indicate a model supported by the second network device or configuration information of a supported model, and the model is an AI model or an ML model.

[0511] Optionally, at least one second identification information may include the first identification information, or the model corresponding to at least one second identification information may include the first model corresponding to the first identification information.

[0512] In a possible design, the transceiver module 1001 is further configured to send first cell information to a second network device. The first cell information may be used to indicate the cell in which the first identification information is received.

[0513] In a possible design, the transceiver module 1001 is further configured to send the configuration information of the first identification information and / or the first model to a core network element.

[0514] In a possible design, the transceiver module 1001 is further configured to send third indication information to a core network element. The third indication information may be used to indicate the applicable range of the first model.

[0515] In a possible design, the transceiver module 1001 is further configured to send the first identification information to a first network device.

[0516] It should be noted that the above transceiver module 1001 may include a receiving module and a sending module ( Figure 10 not shown in the figure). The receiving module is used to receive data and / or signaling from the first network device and / or the second network device; the sending module is used to send data and / or signaling to the first network device and / or the second network device and / or the core network element. The specific implementation manner of the transceiver module 1001 in this application is not specifically limited.

[0517] Optionally, the communication device 1000 may further include a storage module ( Figure 10 not shown in the figure), and the storage module stores programs or instructions. When the processing module 1002 executes the programs or instructions, the communication device 1000 can execute Figures 4 - 9 the functions of the terminal device in the communication method shown.

[0518] It should be noted that the communication device 1000 may be Figure 1 the terminal device shown in Figure 3 or the communication device 300 shown in

[0519] or a chip (system) or other components or assemblies that can be set in the terminal device. This application does not make any limitations in this regard. Figures 4 - 9 In addition, the technical effects of the communication device 1000 can refer to the technical effects of the communication method shown in

[0520] Figure 11 is the structural schematic diagram of the communication device provided by the embodiment of the present application. Figure 3 This communication device is applicable toFigure 1 In the communication system shown, perform Figures 4 - 9 the functions of the second network device in the communication method shown. For ease of explanation, Figure 11 only the main components of the communication device are shown.

[0521] As Figure 11 shown, the communication device 1100 includes: a transceiver module 1101 and a processing module 1102.

[0522] The processing module 1102 is configured to obtain first identification information. Among them, the first identification information is used to identify the configuration of the first model, and the first model is an artificial intelligence (AI) model or a machine learning (ML) model.

[0523] The transceiver module 1101 is configured to send first indication information to the terminal device. Among them, the first indication information is used to indicate that the terminal device adopts the configuration information of the first model corresponding to the first identification information.

[0524] In a possible design, the first identification information may include one or more of the following: an identification of the configuration information of the first model, a name of the first model, and a function of the first model.

[0525] In a possible design, the configuration information of the first model may include parameters of the first model, hyperparameters of the first model, and / or an algorithm of the first model.

[0526] In a possible design, the processing unit is further configured to determine at least one third identification information, and the transceiver module 1101 is further configured to, if at least one of the third identification information includes the first identification information, send the first indication information to the terminal device. Among them, the third identification information may be used to indicate the first model available to the terminal device or the configuration information of the first model.

[0527] In a possible design, the transceiver module 1101 is further configured to, if at least one of the third identification information does not include the first identification information, send the configuration information of at least one first model corresponding to at least one of the third identification information to the terminal device.

[0528] In a possible design, the transceiver module 1101 is further configured to send at least one second identification information to the terminal device. Among them, the second identification information may be used to indicate the models supported by the communication device 1100 or the configuration information of the supported models, and the models are AI models or ML models.

[0529] In a possible design, the transceiver module 1101 is further configured to receive the first identification information from the terminal device.

[0530] In a possible design, the transceiver module 1101 is further configured to receive first identification information from a first network device and / or configuration information of a first model. The configuration information of the first model includes the first identification information.

[0531] In a possible design, the transceiver module 1101 is further configured to receive first identification information from a core network element and / or configuration information of a first model.

[0532] In a possible design, the transceiver module 1101 is further configured to receive first cell information from a terminal device. The first cell information may be used to indicate the cell in the first network device that sends the first identification information.

[0533] It should be noted that the above transceiver module 1101 may include a receiving module and a sending module ( Figure 11 not shown in the figure). The receiving module is configured to receive data and / or signaling from a terminal device and / or a first network device and / or a core network element; the sending module is configured to send data and / or signaling to a terminal device and / or a first network device and / or a core network element. The present application does not make specific limitations on the specific implementation manner of the transceiver module 1101.

[0534] Optionally, the communication device 1100 may further include a storage module ( Figure 11 not shown in the figure), and the storage module stores programs or instructions. When the processing module 1102 executes the programs or instructions, the communication device 1100 can perform Figures 4 - 9 the functions of the second network device in the communication method shown.

[0535] It should be noted that the communication device 1100 may be Figure 1 the second network device shown or Figure 3 the communication device 300 shown, or may also be a chip (system) or other components or assemblies that can be disposed in the second network device. The present application does not make limitations thereon.

[0536] In addition, the technical effects of the communication device 1100 may refer to the technical effects of the communication method shown in Figures 4 - 9 , which will not be elaborated herein.

[0537] Figure 12 is a schematic structural diagram of a communication device provided by an embodiment of the present application. Figure 3 This communication device can be applied to Figure 1 the communication system shown, and perform Figure 4 , Figure 7 the functions of the core network element in the communication method shown. For ease of description, Figure 12 only the main components of this communication device are shown.

[0538] As Figure 12 shown, the communication device 1200 includes: a transceiver module 1201 and a processing module 1202.

[0539] The processing module 1202 is configured to obtain first identification information. The first identification information is used to identify the configuration of a first model, and the first model is an artificial intelligence (AI) model or a machine learning (ML) model.

[0540] The transceiver module is configured to send the first identification information to a second network device.

[0541] In a possible design, the first identification information may include one or more of the following: an identification of the configuration information of the first model, a name of the first model, and a function of the first model.

[0542] In a possible design, the transceiver module 1201 is further configured to receive the configuration information of the first model from a terminal device. The configuration information of the first model may include the first identification information.

[0543] In a possible design, the transceiver module 1201 is further configured to receive the configuration information of the first model from a first network device.

[0544] Optionally, the configuration information of the first model may include parameters of the first model, hyperparameters of the first model, and / or an algorithm of the first model.

[0545] In a possible design, the transceiver module 1201 is further configured to receive third indication information from the first network device. The third indication information is used to indicate the applicable scope of the first model.

[0546] In a possible design, the transceiver module 1201 is further configured to receive the third indication information from the terminal device.

[0547] Optionally, the applicable scope of the first model may include information about a list of applicable public land mobile networks and / or information about a list of applicable cells.

[0548] It should be noted that the above transceiver module 1201 may include a receiving module and a sending module ( Figure 12 not shown in the figure). The receiving module is configured to receive data and / or signaling from the first network device and / or the second network device and / or the terminal device; the sending module is configured to send data and / or signaling to the first network device and / or the second network device and / or the terminal device. The present application does not specifically limit the specific implementation manner of the transceiver module 1201.

[0549] Optionally, the communication device 1200 may further include a storage module ( Figure 12(not shown in the figure), the storage module stores programs or instructions. When the processing module 1202 executes the programs or instructions, the communication device 120 can execute Figure 4 、 Figure 7 the functions of the core network elements in the communication method shown.

[0550] It should be noted that the communication device 1200 can be Figure 1 the core network element shown or Figure 3 the communication device 300 shown, or can also be a chip (system) or other components or assemblies that can be set in the core network element. This application does not make any limitations in this regard.

[0551] In addition, the technical effects of the communication device 1200 can refer to Figure 4 、 Figure 7 the technical effects of the communication method shown, which will not be elaborated here.

[0552] Figure 13 is the structural schematic diagram of the communication device provided by the embodiments of the present application. Figure 4 。This communication device can be applied to Figure 1 the communication system shown, and execute Figures 4 - 9 the functions of the first network device in the communication method shown. For the convenience of description, Figure 13 only the main components of this communication device are shown.

[0553] As Figure 13 shown, the communication device 1300 includes: a sending module 1301.

[0554] The sending module 1301 is used to send the configuration information of the first model to the terminal device. Among them, the configuration information of the first model includes first identification information, and the first identification information is used to identify the configuration of the first model. The first model is an artificial intelligence (AI) model or a machine learning (ML) model.

[0555] Optionally, the first identification information may include one or more of the following: the identification of the configuration information of the first model, the name of the first model, and the function of the first model.

[0556] Optionally, the configuration information of the first model may include the parameters of the first model, the hyperparameters of the first model, and / or the algorithm of the first model.

[0557] In a possible design, the sending module 1301 is further used to send second indication information to the terminal device. Among them, the second indication information can be used to indicate the applicable range and / or the valid time of the first model.

[0558] Optionally, the applicable range of the first model may include the applicable public land mobile network list information and / or the applicable cell list information.

[0559] In a possible design, the sending module 1301 is further configured to send the configuration information of the first model to a core network element.

[0560] In a possible design, the sending module 1301 is further configured to send third indication information to a core network element. The third indication information can be used to indicate the applicable scope of the first model.

[0561] In a possible design, the sending module 1301 is further configured to send the configuration information of the first model to a second network device.

[0562] In a possible design, the sending module 1301 is further configured to send the configuration information of the first model to a terminal device in a broadcast manner.

[0563] In a possible design, the communication device 1300 further includes: a receiving module 1302. The receiving module 1302 is configured to receive first identification information from a terminal device.

[0564] It should be noted that the receiving module 1302 and the sending module 1301 can be separately provided or integrated into one module, that is, a transceiver module ( Figure 13 not shown in the figure). The present application does not specifically limit the specific implementation manners of the receiving module 1302 and the sending module 1301.

[0565] Optionally, the communication device 1300 may further include a processing module 1303 and a storage module ( Figure 13 not shown in the figure), and the storage module stores programs or instructions. When the processing module 1303 executes the programs or instructions, the communication device 1300 can perform Figures 4 - 9 the functions of the first network device in the communication method shown.

[0566] Optionally, the processing module 1303 may be configured to determine the configuration information of the first model and / or the applicable scope of the first model and / or the valid time of the first model.

[0567] It should be noted that the communication device 1300 may be Figure 1 the first network device shown or Figure 3 the communication device 300 shown, or may be a chip (system) or other components or assemblies that can be set in the first network device. The present application does not make any limitations thereto.

[0568] In addition, Figure 13 the technical effects of the communication device 1300 shown can refer to Figures 4 - 9 the technical effects of the communication method shown, which will not be elaborated herein.

[0569] An embodiment of this application provides a communication system. The system includes the above-mentioned terminal device, a first network device, and a second network device.

[0570] Optionally, the communication system may further include a core network element.

[0571] Optionally, the first network device may be the same as the second network device.

[0572] An embodiment of this application provides a computer-readable storage medium, which includes a computer program or instruction; when the computer program or instruction runs on a computer, the computer is caused to execute the communication method described in the foregoing method embodiment.

[0573] An embodiment of this application provides a computer program product, which includes a computer program or instruction. When the computer program or instruction runs on a computer, the computer is caused to execute the communication method described in the foregoing method embodiment.

[0574] It should be understood that the processor in the embodiment of this application may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0575] It should also be understood that the memory in the embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0576] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware, or any other combination. When implemented using software, the above embodiments 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 or computer programs. When the computer instructions or computer programs are loaded or 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 terminal device, a network device, a general-purpose computer, a dedicated 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 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 a data center that contains one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0577] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. Additionally, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context before and after.

[0578] In this application, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0579] It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0580] Those of ordinary skill in the art can realize that the units or modules and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0581] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units or modules described above can refer to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0582] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the above-mentioned division of units or modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or modules can be combined or integrated into another system, or some units or modules can be ignored, or their corresponding functions are not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces, and the indirect coupling or communication connection of the device or unit / module can be in an electrical, mechanical or other form.

[0583] The unit / module described as a separated component may or may not be physically separated, and the component displayed as a unit / module may or may not be a physical unit / module, that is, it may be located in one place, or may be distributed to multiple network units / modules. Some or all of the units / modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0584] In addition, the functional units / modules in each embodiment of this application can be integrated in one processing unit / module, or each unit / module can exist physically alone, or two or more units / modules can be integrated in one unit / module.

[0585] When the above-mentioned functions are implemented in the form of software functional units / modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art 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 foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0586] In the embodiments of this application, on the premise of no logical contradiction, the embodiments can refer to each other. For example, the methods and / or terms between method embodiments can refer to each other. For example, the functions and / or terms between device embodiments can refer to each other. For example, the functions and / or terms between device embodiments and method embodiments can refer to each other.

[0587] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

1. A communication method, characterized in that, including: receiving configuration information of a first model from a first network device; wherein, the first model is an artificial intelligence (AI) model or a machine learning (ML) model; obtaining first identification information; wherein, the first identification information is used to identify the configuration of the first model; receiving first indication information from a second network device; wherein, the first indication information is used to indicate adopting the configuration information of the first model corresponding to the first identification information; processing data by using the configuration information of the first model.

2. The communication method according to claim 1, wherein The obtaining the first identification information includes: the configuration information of the first model includes the first identification information; or, generating the first identification information.

3. The communication method according to claim 1 or 2, characterized in that, The first identification information includes one or more of the following: an identification of the configuration information of the first model, a name of the first model, and a function of the first model.

4. The communication method according to claim 1 or 2, characterized in that The configuration information of the first model includes parameters of the first model and / or hyperparameters of the first model.

5. The communication method according to claim 1 or 2, characterized in that The method further includes; receiving second indication information from the first network device; wherein, the second indication information is used to indicate a scope of application of the first model and / or a valid time of the first model.

6. The communication method according to claim 5, wherein The scope of application of the first model includes list information of applicable public land mobile networks and / or list information of applicable cells.

7. The communication method according to claim 6, wherein The list information of the public land mobile networks includes registered public land mobile networks of a terminal device.

8. The communication method according to claim 6, wherein The first network device is the same as the second network device; or, a first cell in the first network device and a second cell in the second network device are the same, the first cell is a cell in which the first identification information is received, and the second cell is a cell in which the first identification information is sent; or, the list information of the cells includes the second cell.

9. The communication method according to claim 1 or 2, characterized in that The method further includes: sending the first identification information to the second network device.

10. The communication method according to claim 1 or 2, characterized in that, The method further includes: receiving at least one second identification information from the second network device; wherein, the second identification information is used to indicate a model supported by the second network device or configuration information of a supported model, the model is the AI model or the ML model, the at least one second identification information includes the first identification information, or a model corresponding to the at least one second identification information includes the first model corresponding to the first identification information.

11. The communication method according to claim 1 or 2, characterized in that, The method further includes: sending first cell information to the second network device; wherein, the first cell information is used to indicate a cell in which the first identification information is received.

12. The communication method according to claim 1 or 2, characterized in that, The method further includes: sending the first identification information or the configuration information of the first model to a core network element.

13. The communication method according to claim 1 or 2, characterized in that The method further includes: sending the first identification information to the first network device.

14. A communication method, characterized in that, including: obtaining first identification information; wherein, the first identification information is used to identify a configuration of a first model, the first model is an artificial intelligence (AI) model or a machine learning (ML) model; sending first indication information to a terminal device; wherein, the first indication information is used to indicate that the terminal device adopts the configuration information of the first model corresponding to the first identification information.

15. The communication method according to claim 14, characterized in that, The first identification information includes one or more of the following: an identification of the configuration information of the first model, a name of the first model, and a function of the first model.

16. The communication method according to claim 14 or 15, characterized in that, The configuration information of the first model includes parameters of the first model and / or hyperparameters of the first model.

17. The communication method according to claim 14 or 15, characterized in that, The method further includes: Sending at least one second identification information to the terminal device; wherein, the second identification information is used to indicate a model supported by the second network device or configuration information of the supported model, and the model is the AI model or the ML model.

18. The communication method according to claim 14 or 15, characterized in that, The obtaining of the first identification information includes: Receiving the first identification information from the terminal device; or, Receiving the first identification information from the first network device or the configuration information of the first model; wherein, the configuration information of the first model includes the first identification information; or, Receiving the first identification information from a core network element or the configuration information of the first model.

19. A communication device, characterized in that, Comprising a processor and a memory, the memory is coupled to the processor, and the processor is configured to execute the method according to any one of claims 1-18.

20. A communication device, characterized in that, Comprising a processor and a communication interface, the processor uses the communication interface to execute the method according to any one of claims 1-18.

21. A computer-readable storage medium, characterized in that, A computer program or instruction is stored on the computer-readable storage medium, and when the computer program or instruction runs on a computer, the computer is caused to execute the communication method according to any one of claims 1-18.

Images