Information transmission method and device

Abstract

The invention provides an information transmission method and device which are used for transmitting task data. In the method, first information is obtained, and the first information comprises a mapping relation between first task information and first bearing information. And sending the data information of the first task indicated by the first task information to the network equipment through the first bearer indicated by the first bearer information. Based on the scheme, the terminal equipment can determine the bearer capable of sending the data information of the task corresponding to the task information according to the mapping relation between the task information and the bearer information. Through the mapping relation, the terminal equipment and the network equipment can support the transmission of the data information of the task through a plurality of bearers, and the transmission efficiency of the data information of the task can be improved.

Description

Information transmission method and device Technical Field

[0001] The present application relates to the field of wireless communication technology, and in particular to an information transmission method and device. Background Art

[0002] During the execution of tasks such as computing, artificial intelligence (AI) reasoning, AI training, and data processing, task data needs to be exchanged between network elements and user equipment (UE). For example, the UE in a computing task obtains input from the base station side and performs calculations, and reports the final calculation results to the base station. For another example, the UE in an AI training task reports gradient information to the base station, and the base station sends the updated global model to the UE. For another example, the UE in AI reasoning reports the inference value to the base station.

[0003] However, existing signaling bearers and data bearers cannot directly transmit the above task data. Therefore, how to exchange task information between network elements and UEs has become an urgent problem to be solved.

[0004] Summary of the Invention

[0005] The present application provides an information transmission method and apparatus for transmitting task data.

[0006] In a first aspect, an information transmission method is provided. This method can be performed by a terminal device, or by a chip / chip system. In this method, first information is obtained, where the first information includes a mapping relationship between first task information and first bearer information. Data information of a first task indicated by the first task information is transmitted to a network device via a first bearer indicated by the first bearer information.

[0007] Based on this solution, the terminal device can determine the bearer on which the task data corresponding to the task information can be transmitted based on the mapping relationship between the task information and the bearer information. Through this mapping relationship, the terminal device and the network device can support the transmission of task data information via multiple bearers, which can improve the transmission efficiency of task data information.

[0008] In a possible implementation, the first information further includes a mapping relationship between the second task information and the first bearer information. The first task information is different from the second task information. The data information of the first task further includes the first task information.

[0009] Based on this solution, when different task information corresponds to the same bearer information, the terminal device can also send corresponding task information when sending task data information to the network device to inform the network device which task information the sent data information belongs to.

[0010] In one possible implementation, a first AI model used to perform a first task is processed. The data information of the first task also includes a processing result of the first AI model. Based on this solution, the terminal device supports processing the AI ​​model and can send the processing result of the AI ​​model to the network device.

[0011] In one possible implementation, first configuration information is received from a network device, where the first configuration information includes a mapping relationship between first task information and a processing method of an AI model, or a mapping relationship between first bearer information and a processing method of the AI ​​model. Processing the first AI model for executing the first task includes: processing the first AI model according to the processing method of the AI ​​model corresponding to the first task information. Alternatively, processing the processing method of the AI ​​model according to the processing method of the AI ​​model corresponding to the first bearer information.

[0012] Based on the above solution, the network device can configure the corresponding AI model processing method for the bearer information or task information, so that the terminal device can process the AI ​​model according to the processing method of the AI ​​model corresponding to the bearer information or task information.

[0013] In one possible implementation, the AI ​​model processing method includes: a switch configuration of the AI ​​model and / or a parameter configuration of the AI ​​model. The switch configuration of the AI ​​model includes on or off. When the switch configuration of the AI ​​model is on, the switch configuration of the AI ​​model is used to indicate that the first AI model is to be processed. When the switch configuration of the AI ​​model is off, the switch configuration of the AI ​​model is used to indicate that the first AI model is not to be processed.

[0014] Based on the above solution, the network device can configure the switch configuration and / or parameter configuration of the AI ​​model processing method to allow the terminal device to process the AI ​​model based on the configuration of the network device.

[0015] In one possible implementation, AI model processing includes enabling and / or configuring parameters for one or more of model compression, model pruning, model security, model privacy, inference, data processing, and training. Based on this solution, the terminal device can perform different processing on the AI ​​model.

[0016] In one possible implementation, the data information of the first task also includes format information, which indicates the format of the processing method. Based on this solution, the terminal device can flexibly select the processing method format based on changes in its own environment, process the AI ​​model, and send the selected format information to the network device, allowing the network device to determine the format information used by the terminal device when processing the AI ​​model.

[0017] In a possible implementation, the first bearer information includes one or more of the type of the first bearer, an identifier of the first bearer, and a logical channel identity (LCID) of the first bearer.

[0018] In one possible implementation, the data information of the first task includes first indication information, the first indication information being used to indicate that the first bearer is a signaling bearer. Alternatively, the data information of the first task includes second indication information, the second indication information being used to indicate that the first bearer is a data bearer.

[0019] Based on this solution, the first indication information can be used to indicate whether the first bearer is a data bearer or a signaling bearer, thereby reducing excessive occupation of the LCID by the signaling bearer.

[0020] In one possible implementation, obtaining second configuration information, the second configuration information including a mapping relationship between first bearer information and quality of service (QoS) information, and sending data information of a first task indicated by first task information to a network device via a first bearer indicated by the first bearer information includes: sending the data information of the first task indicated by the first task information to the network device via the first bearer indicated by the first bearer information according to the QoS information corresponding to the first bearer information, where the first bearer is a signaling bearer.

[0021] Based on this solution, through the second configuration information, the terminal device can send data information of the first task based on the QoS information, thereby achieving differentiated QoS guarantee.

[0022] In one possible implementation, the first bearer is a signaling bearer or a data bearer, and the LCID of the signaling bearer is different from the LCID of the data bearer. Based on this solution, by configuring different LCIDs for the signaling bearer and the data bearer, excessive LCID occupation by the signaling bearer can be reduced.

[0023] In one possible implementation, the data information of the first task includes third indication information, which instructs the network device to transparently transmit the data information of the first task, and the first bearer is a data bearer. Alternatively, the data information of the first task includes fourth indication information, which instructs the network device to terminate the data information of the first task, and the first bearer is a data bearer.

[0024] Based on this solution, the terminal device can indicate to the network device through the third indication information whether the data information carried by the first bearer is to be transparently transmitted or terminated, so that the data information of the task can be reached by the network device.

[0025] In one possible implementation, the data information of the first task further includes one or more items of information included in the first bearer information and / or one or more items of information included in the first task information. The one or more items of information included in the first bearer information and / or one or more items of information included in the first task information are used to indicate whether the network device terminates the first bearer, where the first bearer is a data bearer.

[0026] Based on this solution, through the first bearer information and the first task information, the terminal device can indicate to the network device whether the data information carried by the first bearer is to be transparently transmitted or terminated, so that the data information of the task can be reached by the network device.

[0027] In one possible implementation, the data information of the first task also includes one or more of a node type, a node identifier, first bearer information, and first task information, and the node type, node identifier, first bearer information, and first task information are used to indicate the node that terminates the data information of the first task.

[0028] Based on this solution, through one or more of the above information, the terminal device can indicate to the network device the node that terminates the data information of the first task, thereby allowing the network device to route the data information of the first task.

[0029] In one possible implementation, third configuration information is obtained, where the third configuration information includes a mapping relationship between the first bearer information and a node, and the node is used to terminate the first bearer. Alternatively, the third configuration information includes a mapping relationship between the first task information and a node, and the node is used to terminate the first bearer.

[0030] Based on this solution, the terminal device can determine the node that terminates the data information of the first task according to the third configuration information, so that the terminal device can carry relevant information when sending the data information of the first task and indicate to the network device the node that terminates the data information of the first task.

[0031] In a second aspect, an information transmission method is provided. This method can be performed by a network device, or by a chip / chip system. In this method, first information is sent to a terminal device, where the first information includes a mapping relationship between first task information and first bearer information. Data information of a first task indicated by the first task information from the terminal device is received via a first bearer indicated by the first bearer information.

[0032] In a possible implementation, the first information further includes a mapping relationship between the second task information and the first bearer information. The first task information is different from the second task information. The data information of the first task further includes the first task information.

[0033] In one possible implementation, the data information of the first task also includes a processing result of the terminal device processing the first AI model used to execute the first task.

[0034] In one possible implementation, first configuration information is sent to the terminal device, where the first configuration information includes a mapping relationship between the first task information and the processing method of the AI ​​model, or a mapping relationship between the first bearer information and the processing method of the AI ​​model.

[0035] In one possible implementation, the AI ​​model processing method includes: a switch configuration of the AI ​​model and / or a parameter configuration of the AI ​​model. The switch configuration of the AI ​​model includes on or off. When the switch configuration of the AI ​​model is on, the switch configuration of the AI ​​model is used to indicate that the first AI model is to be processed. When the switch configuration of the AI ​​model is off, the switch configuration of the AI ​​model is used to indicate that the first AI model is not to be processed.

[0036] In one possible implementation, the AI ​​model processing method includes: switch configuration and / or parameter configuration of one or more of model compression, model pruning, model security, model privacy, reasoning, data processing and training.

[0037] In a possible implementation, the data information of the first task further includes format information, where the format information is used to indicate the format of the processing method.

[0038] In a possible implementation manner, the first bearer information includes one or more of the type of the first bearer, the identifier of the first bearer, and the logical channel identifier LCID of the first bearer.

[0039] In one possible implementation, the data information of the first task includes first indication information, the first indication information being used to indicate that the first bearer is a signaling bearer. Alternatively, the data information of the first task includes second indication information, the second indication information being used to indicate that the first bearer is a data bearer.

[0040] In a possible implementation manner, second configuration information is sent to the terminal device, where the second configuration information includes a mapping relationship between the first bearer information and the quality of service QoS information.

[0041] In a possible implementation, the first bearer is a signaling bearer or a data bearer, and a logical channel identifier LCID of the signaling bearer is different from an LCID of the data bearer.

[0042] In one possible implementation, the data information of the first task includes third indication information, which instructs the network device to transparently transmit the data information of the first task, and the first bearer is a data bearer. Alternatively, the data information of the first task includes fourth indication information, which instructs the network device to terminate the data information of the first task, and the first bearer is a data bearer.

[0043] In one possible implementation, the data information of the first task further includes one or more items of information included in the first bearer information and / or one or more items of information included in the first task information. The one or more items of information included in the first bearer information and / or one or more items of information included in the first task information are used to indicate whether the network device terminates the first bearer, where the first bearer is a data bearer.

[0044] In one possible implementation, the data information of the first task also includes one or more of a node type, a node identifier, first bearer information, and first task information, and the node type, node identifier, first bearer information, and first task information are used to indicate the node that terminates the data information of the first task.

[0045] In one possible implementation, third configuration information is sent to the terminal device. The third configuration information includes a mapping relationship between the first bearer information and a node, and the node is used to terminate the first bearer. And / or the third configuration information includes a mapping relationship between the first task information and a node, and the node is used to terminate the first bearer.

[0046] In one possible implementation, fourth configuration information is sent to each node. The fourth configuration information includes a mapping relationship between the first bearer information and the node, and the node is configured to terminate the first bearer. Alternatively, the fourth configuration information includes a mapping relationship between the first task information and the node, and the node is configured to terminate the first bearer.

[0047] In a third aspect, a communication device is provided, including: a processing unit and a transceiver unit.

[0048] The processing unit is configured to obtain first information, wherein the first information includes a mapping relationship between first task information and first bearer information. The transceiver unit is configured to send data information of the first task indicated by the first task information to the network device via the first bearer indicated by the first bearer information.

[0049] In a possible implementation, the first information further includes a mapping relationship between the second task information and the first bearer information. The first task information is different from the second task information. The data information of the first task further includes the first task information.

[0050] In one possible implementation, the processing unit is further configured to process a first AI model used to perform the first task. The data information of the first task also includes a processing result of the first AI model.

[0051] In one possible implementation, the transceiver unit is further configured to receive first configuration information from a network device, where the first configuration information includes a mapping relationship between first task information and a processing method of the AI ​​model, or a mapping relationship between first bearer information and a processing method of the AI ​​model. The processing unit is specifically configured to process the first AI model according to the processing method of the AI ​​model corresponding to the first task information. Alternatively, the processing unit is specifically configured to process the processing method of the AI ​​model according to an identifier of the first bearer information and the processing method of the AI ​​model.

[0052] In one possible implementation, the processing mode of the AI ​​model includes: a switch configuration of the processing mode of the AI ​​model and / or a parameter configuration of the processing mode of the AI ​​model. The switch configuration of the processing mode of the AI ​​model includes on or off. When the switch configuration of the processing mode of the AI ​​model includes on, the switch configuration of the processing mode of the AI ​​model is used to indicate that the first AI model is to be processed. When the switch configuration of the processing mode of the AI ​​model includes off, the switch configuration of the processing mode of the AI ​​model is used to indicate that the first AI model is not to be processed.

[0053] In one possible implementation, the AI ​​model is processed in a manner that includes one or more of: model compression, model pruning, model security, model privacy, reasoning, data processing, and training.

[0054] In a possible implementation, the data information of the first task further includes format information, where the format information is used to indicate the format of the processing method.

[0055] In a possible implementation manner, the first bearer information includes one or more of the type of the first bearer, the identifier of the first bearer, and the logical channel identifier LCID of the first bearer.

[0056] In one possible implementation, the data information of the first task includes first indication information, the first indication information being used to indicate that the first bearer is a signaling bearer. Alternatively, the data information of the first task includes second indication information, the second indication information being used to indicate that the first bearer is a data bearer.

[0057] In one possible implementation, the processing unit is further configured to: obtain second configuration information, the second configuration information including a mapping relationship between the first bearer information and the quality of service (QoS) information. The transceiver unit is specifically configured to send data information of the first task indicated by the first task information to the network device via a first bearer indicated by the first bearer information according to the QoS information corresponding to the first bearer information, where the first bearer is a signaling bearer.

[0058] In a possible implementation, the first bearer is a signaling bearer or a data bearer, and the LCID of the signaling bearer is different from the LCID of the data bearer.

[0059] In one possible implementation, the data information of the first task includes third indication information, which instructs the network device to transparently transmit the data information of the first task, and the first bearer is a data bearer. Alternatively, the data information of the first task includes fourth indication information, which instructs the network device to terminate the data information of the first task, and the first bearer is a data bearer.

[0060] In one possible implementation, the data information of the first task also includes one or more items of information contained in the first bearer information and one or more items of information contained in the first task information. The first bearer information and one or more items of the first task information are used to indicate whether the network device terminates the first bearer, and the first bearer is a data bearer.

[0061] In one possible implementation, the data information of the first task also includes one or more of a node type, a node identifier, first bearer information, and first task information, and the node type, node identifier, first bearer information, and first task information are used to indicate the node that terminates the data information of the first task.

[0062] In one possible implementation, the processing unit is further configured to obtain third configuration information, where the third configuration information includes a mapping relationship between the first bearer information and a node, and the node is configured to terminate the first bearer. Furthermore, the third configuration information includes a mapping relationship between the first task information and a node, and the node is configured to terminate the first bearer.

[0063] In a fourth aspect, a communication device is provided, comprising: a processing unit and a transceiver unit.

[0064] The processing unit is configured to generate first information. The transceiver unit is configured to send the first information to the terminal device, wherein the first information includes a mapping relationship between the first task information and the first bearer information. The transceiver unit is further configured to receive data information of the first task indicated by the first task information from the terminal device via the first bearer indicated by the first bearer information.

[0065] In a possible implementation, the first information further includes a mapping relationship between the second task information and the first bearer information. The first task information is different from the second task information. The data information of the first task further includes the first task information.

[0066] In one possible implementation, the data information of the first task also includes a processing result of the terminal device processing the first AI model used to execute the first task.

[0067] In one possible implementation, the transceiver unit is further used to send first configuration information to the terminal device, where the first configuration information includes a mapping relationship between the first task information and the processing method of the AI ​​model, or a mapping relationship between the first bearer information and the processing method of the AI ​​model.

[0068] In one possible implementation, the processing mode of the AI ​​model includes: a switch configuration of the processing mode of the AI ​​model and / or a parameter configuration of the processing mode of the AI ​​model. The switch configuration of the processing mode of the AI ​​model includes on or off. When the switch configuration of the processing mode of the AI ​​model includes on, the switch configuration of the processing mode of the AI ​​model is used to indicate that the first AI model is to be processed. When the switch configuration of the processing mode of the AI ​​model includes off, the switch configuration of the processing mode of the AI ​​model is used to indicate that the first AI model is not to be processed.

[0069] In one possible implementation, the AI ​​model is processed in a manner that includes one or more of: model compression, model pruning, model security, model privacy, reasoning, data processing, and training.

[0070] In a possible implementation, the data information of the first task further includes format information, where the format information is used to indicate the format of the processing method.

[0071] In a possible implementation manner, the first bearer information includes one or more of the type of the first bearer, the identifier of the first bearer, and the logical channel identifier LCID of the first bearer.

[0072] In one possible implementation, the data information of the first task includes first indication information, the first indication information being used to indicate that the first bearer is a signaling bearer. Alternatively, the data information of the first task includes second indication information, the second indication information being used to indicate that the first bearer is a data bearer.

[0073] In a possible implementation, the transceiver unit is further configured to send second configuration information to the terminal device, where the second configuration information includes a mapping relationship between the first bearer information and the quality of service QoS information.

[0074] In a possible implementation, the first bearer is a signaling bearer or a data bearer, and a logical channel identifier LCID of the signaling bearer is different from an LCID of the data bearer.

[0075] In one possible implementation, the data information of the first task includes third indication information, which instructs the network device to transparently transmit the data information of the first task, and the first bearer is a data bearer. Alternatively, the data information of the first task includes fourth indication information, which instructs the network device to terminate the data information of the first task, and the first bearer is a data bearer.

[0076] In one possible implementation, the data information of the first task also includes one or more items of information contained in the first bearer information and one or more items of information contained in the first task information. The first bearer information and one or more items of the first task information are used to indicate whether the network device terminates the first bearer, and the first bearer is a data bearer.

[0077] In one possible implementation, the data information of the first task also includes one or more of a node type, a node identifier, first bearer information, and first task information, and the node type, node identifier, first bearer information, and first task information are used to indicate the node that terminates the data information of the first task.

[0078] In one possible implementation, the transceiver unit is further configured to send third configuration information to the terminal device, where the third configuration information includes a mapping relationship between the first bearer information and a node, and the node is configured to terminate the first bearer. Furthermore, the third configuration information includes a mapping relationship between the first task information and a node, and the node is configured to terminate the first bearer.

[0079] In one possible implementation, the transceiver unit is further configured to send fourth configuration information to each node, where the fourth configuration information includes a mapping relationship between the first bearer information and the node, and the node is configured to terminate the first bearer. Furthermore, the fourth configuration information includes a mapping relationship between the first task information and the node, and the node is configured to terminate the first bearer.

[0080] In a fifth aspect, a communication device is provided. The communication device may be the communication device in any possible implementation of the third aspect or the fourth aspect of the above-mentioned embodiment, or a chip provided in the communication device in any of the third aspect or the fourth aspect. The communication device includes a communication interface and a processor, and optionally, a memory. The memory is used to store computer programs, instructions, or data, and the processor is coupled to the memory and the communication interface. When the processor reads the computer program, instructions, or data, the communication device executes the method executed by the terminal device in any possible implementation of the first aspect, or executes the method executed by the network device in any possible implementation of the second aspect.

[0081] It should be understood that the communication interface can be implemented by an antenna, a feeder, a codec, etc. in the communication device, or, if the communication device is a chip provided in a network device or a terminal device, the communication interface can be an input / output interface of the chip, such as an input / output pin, etc. The communication device may also include a transceiver for communicating with other devices.

[0082] In a sixth aspect, an embodiment of the present application provides a chip system, which includes a processor and may also include a memory, for implementing the method executed by a terminal device or a network device in any possible implementation of the first aspect or the second aspect. In one possible implementation, the chip system also includes a memory for storing program instructions and / or data. The chip system can be composed of a chip, or it can include a chip and other discrete devices.

[0083] In a seventh aspect, the present application provides a computer-readable storage medium, which stores a computer program or instruction. When the computer program or instruction is executed, the method performed by the terminal device or network device in the above aspects is implemented.

[0084] In an eighth aspect, a computer program product is provided, comprising: computer program code or instructions, which, when executed, causes the methods performed by the terminal device or network device in the above aspects to be executed.

[0085] In a ninth aspect, a communication device is provided, which includes a unit or module for executing the above-mentioned methods.

[0086] In a tenth aspect, a chip system is provided, comprising a logic circuit and an input / output interface. The logic circuit is configured to execute the method executed by the terminal device or network device described above. The input / output interface is configured to communicate with other devices.

[0087] The beneficial effects of the above-mentioned second to tenth aspects and their implementation methods can refer to the description of the beneficial effects of the method of the first aspect and its implementation method. BRIEF DESCRIPTION OF THE DRAWINGS

[0088] FIG1 is a schematic diagram of a communication system provided in an embodiment of the present application;

[0089] FIG2 is a schematic diagram of a user plane protocol and a control plane protocol of a terminal device and a network device;

[0090] Figure 3 is a schematic diagram of a scenario of an AI task;

[0091] FIG4A is a schematic diagram of an SRB protocol stack;

[0092] FIG4B is a schematic diagram of a DRB protocol stack;

[0093] FIG5 is an exemplary flow chart of a data transmission method provided in an embodiment of the present application;

[0094] FIG6 is a schematic diagram of a MAC subheader provided in an embodiment of the present application;

[0095] FIG7 is a schematic diagram of a user plane protocol stack provided in an embodiment of the present application;

[0096] FIG8 is a schematic diagram of a protocol stack in a CU-DU separation deployment scenario provided by an embodiment of the present application;

[0097] FIG9 is a schematic diagram of a data information routing method provided in an embodiment of the present application;

[0098] FIG10 is a schematic diagram of another data information routing method provided in an embodiment of the present application;

[0099] FIG11 is a schematic diagram of a communication device provided in an embodiment of the present application;

[0100] FIG12 is a schematic diagram of another communication device provided in an embodiment of the present application;

[0101] FIG13 is a schematic diagram of another communication device provided in an embodiment of the present application;

[0102] FIG14 is a schematic diagram of another communication device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0103] The following describes the technical solutions provided by the embodiments of the present application in conjunction with the accompanying drawings.

[0104] The following describes a communication system to which the method provided in the embodiment of the present application is applicable, with reference to FIG1 . Referring to FIG1 , a communication system 100 includes a network device 101 and a terminal device 102 .

[0105] The terminal devices involved in this application include devices that provide voice and / or data connectivity to users, and more specifically, include devices that provide voice to users, or devices that provide data connectivity to users, or devices that provide both voice and data connectivity to users. For example, they may include handheld devices with wireless connection capabilities, or processing devices connected to wireless modems. The terminal device may be user equipment (UE), wireless terminal device, mobile terminal device, device-to-device (D2D) terminal device, vehicle-to-everything (V2X) terminal device, machine-to-machine / machine-type communications (M2M / MTC) terminal device, Internet of Things (IoT) terminal device, subscriber unit, subscriber station, mobile station, remote station, access point (AP), remote terminal device, access terminal device, user terminal device, user agent, or user equipment, satellite, drone, balloon or aircraft, etc. For example, it may include a mobile phone (or so-called "cellular" phone), a computer with a mobile terminal device, a portable, pocket-sized, handheld, or computer-built-in mobile device, etc. For example, personal communication service (PCS) phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), and other devices. Also included are restricted devices, such as devices with low power consumption, or devices with limited storage capacity, or devices with limited computing power. For example, information sensing devices such as barcodes, radio frequency identification (RFID), sensors, global positioning systems (GPS), laser scanners, etc. As an example and not a limitation, in the embodiments of the present application, the terminal device may also be a wearable device.Wearable devices, also known as wearable smart devices or smart wearable devices, are a general term for wearable devices developed by applying wearable technology to intelligently design and develop wearable devices for everyday wear. The various terminal devices described above, if located in a vehicle (e.g., placed inside or installed in the vehicle), can be considered in-vehicle terminal devices, also known as on-board units (OBUs).

[0106] The network devices involved in this application include access network (AN) devices, such as base stations or access points, which can refer to devices in the access network that communicate with wireless terminal devices through one or more cells at the air interface, or transmission points (TRP), transmitting points (TP), mobile switching centers, and devices that perform base station functions in device-to-device (D2D), vehicle-to-everything (V2X), and machine-to-machine (M2M) communications. Alternatively, the network device can also be a road side unit (RSU) in vehicle-to-everything (V2X) technology. The network device may include an evolved base station (eNB or e-NodeB, evolved Node B) in a long term evolution (LTE) system or an advanced long term evolution (LTE-A), or may also include a next generation node B (gNB) in a new radio (NR) system, or an access network device in a future evolved communication system such as the sixth generation (6G). In addition, in a network structure, the network device may include a centralized unit (CU), a distributed unit (DU), or both a CU and a DU. The access network device including the CU and the DU may split the protocol layer of the base station, with the functions of some protocol layers being centrally controlled by the CU, and the functions of the remaining part or all of the protocol layers being distributed in the DU, with the CU centrally controlling the DU. In addition, the functions of the CU may be further divided. For example, the control plane (CP) and the user plane (UP) may be separated, that is, into the CU control plane (CU-CP) and the CU user plane (CU-UP). For example, the CU-CP and CU-UP can be implemented by different functional entities. The CU-CP and CU-UP can be coupled with the DU to jointly complete the functions of the network device. The CU-CP can also be divided into CU-CP1 and CU-CP2.CU-CP1 includes various radio resource management functions, and CU-CP2 includes radio resource control (RRC) functions and control plane signaling functions at the packet data convergence protocol (PDCP) layer.

[0107] Optionally, the communication system shown in Figure 1 may further include a core network (not shown). As the core part of the mobile communication network, the core network equipment plays a connecting role and is mainly responsible for handling terminal device mobility management, session management, and data transmission.

[0108] In the embodiments of the present application, the device for implementing the function of the terminal device can be the terminal device; it can also be a device that can support the terminal device to implement the function, such as a chip system. The device can be installed in the terminal device or used in conjunction with the terminal device. In the embodiments of the present application, the chip system can be composed of a chip or include a chip and other discrete devices.

[0109] In the embodiments of the present application, the device for implementing the function of the network device can be the network device; or it can be a device that can support the network device to implement the function, such as a chip system. The device can be installed in the network device or used in conjunction with the network device.

[0110] The embodiments of the present application are also applicable to communication between terminal devices, satellite communication, etc.

[0111] The embodiments of the present application are applicable to both homogeneous and heterogeneous network scenarios. There are no restrictions on the transmission points, and they can be multi-point coordinated transmission between macro base stations, micro base stations, and macro base stations. They are applicable to both frequency division duplexing (FDD) and time division duplexing (TDD) systems. The embodiments of the present application are applicable to both low-frequency and high-frequency scenarios, such as terahertz and optical communications.

[0112] The embodiments of the present application can be applied to 5G communication systems, 6G communication systems, or future evolved communication systems, or other communication systems, etc., and the embodiments of the present application are not limited to this. The embodiments of the present application can be applied not only to communication between network devices and terminal devices, but also to communication between network devices and network devices, communication between terminal devices and terminal devices, communication between vehicle networks, Internet of Things, Industrial Internet, etc. The following embodiments of the present application are illustrated by using communication between terminal devices and network devices.

[0113] Referring to Figure 2 , a terminal device in an embodiment of the present application may include a physical layer (PHY), a medium access control (MAC) layer, a radio link control (RLC) layer, a packet data convergence protocol (PDCP) layer, a radio resource control (RRC) layer, and a service data adaptation protocol (SDAP) layer. The terminal device may also include user plane protocols and control plane protocols.

[0114] Network equipment can include PHY, MAC, RLC, PDCP, RRC, and SDAP layers. Network equipment can also include user plane protocols and control plane protocols. Terminal devices and various layers of network equipment can be interconnected to transfer information.

[0115] For ease of description, the following description takes the terminal device as an example and the network device as a base station as an example.

[0116] During the execution of tasks such as computing, AI reasoning, AI training, and data processing in the network, task data needs to be exchanged between network elements and UEs. See Figure 3 for an illustration of how task data is exchanged between network elements and UEs.

[0117] In scenario 1, UE1 completes its calculation and sends Result 1 to the base station. The base station uses Result 1 as input and sends it to UE2, which then continues the calculation. UE2 completes its calculation and sends Result 2 to the base station. The base station uses Result 2 as input and sends it to UE3. UE3 continues its calculation and sends Result 3 to the base station. The base station then uses Result 3.

[0118] Scenario 2 is similar to Scenario 1, except that results 1 and 2 are no longer forwarded by the base station but are transmitted directly between UEs. For example, UE1 completes a calculation and sends result 1 to UE2. UE2 uses result 1 as input for further calculation and sends result 2 to UE3. UE3 uses result 2 as input for further calculation and sends result 3 to the base station. The base station then uses result 3.

[0119] Scenario 3 refers to the scenario where the base station and multiple UEs perform federated learning to jointly train and ultimately obtain an AI model. Since UE data cannot be directly uploaded to the base station for privacy reasons, the UE first performs gradient calculations, and UE1, UE2, and UE3 report and send their respective gradient values ​​to the base station. The base station uses the above multiple gradient information to update the global model and then sends the updated global model to each UE. The UE then performs gradient calculations based on the updated global model and sends it to the base station, thereby starting the next round of model optimization. The corresponding process of federated learning is as follows:

[0120] S1: UE sends a gradient to the base station.

[0121] S2: The base station aggregates the collected gradients sent by one or more UEs and updates the AI ​​model to learn a new AI model.

[0122] S3: The terminal sends the updated AI model to each UE;

[0123] S4: Each UE replaces the latest network model received in S3 with its own AI model for the next step of training and gradient solution.

[0124] Optionally, the UE may perform the next round of training, and the UE may perform gradient solution and send the gradient to the base station, that is, return to execute S1.

[0125] Scenario 4 is a joint reasoning process. In this scenario, multiple UEs first perform reasoning and then send their respective reasoning results to the base station. The base station then performs reasoning based on the reasoning results of multiple UEs and applies the reasoned results.

[0126] In all of the above scenarios, task data is transmitted between the UE and the base station over the air interface. Therefore, how to transmit task data over the air interface is an urgent problem to be solved.

[0127] In existing 4G or 5G systems, the bearers between the UE and the base station are divided into signaling radio bearers (SRBs) and data radio bearers (DRBs). The following describes each of these bearers.

[0128] 1. SRB

[0129] In a 4G or 5G system, a UE has three SRBs, of which SRB0 is the signaling bearer used by the UE to carry RRC messages before entering the connected state. This includes the RRC setup request message and RRC setup response message carried during the random access process. After the UE enters the connected state, the UE establishes SRB1 based on the base station's configuration and uses it to transmit all subsequent RRC signaling. At the same time, the connected UE also establishes SRB2 to transmit non-access stratum (NAS) signaling between the UE and the core network (CN).

[0130] To transmit quality of experience (QoE) to the base station, the standard also defines SRB4 for QoE transmission. In a multi-rate dual connectivity (MR-DC) scenario, the UE is connected to both stations simultaneously. The bearer between the UE and the master node (MN) is SRB1, and the bearer between the UE and the secondary node (SN) is SRB3.

[0131] If MR-DC scenarios and QoE reporting are not considered, the only signaling bearer between the connected UE and the base station is SRB1. The protocol stack corresponding to SRB is shown in Figure 4A. Task resource control (TRC) is an enhancement of the RRC layer in the 5G protocol stack. It builds on the existing radio resource control functions and adds control functions for tasks such as AI, computing, and data processing.

[0132] 2. DRB

[0133] The establishment of a DRB is determined by the base station and the number of services initiated by the UE and the differences in the quality of service (QoS) of these services. Generally, the base station places data streams of multiple UE services with similar QoS into the same DRB for transmission. Based on the base station's configuration, the UE can establish one or more DRB bearers.

[0134] The DRB protocol stack is shown in Figure 4B, where the task resource scheduler (TRS) is an enhancement of the MAC layer in the 5G protocol stack. For example, the computing power scheduling function is added to the existing air interface resource scheduling function of the MAC layer.

[0135] Transmitting the aforementioned task data via SRB or DRB will result in the following problems:

[0136] 1) If SRB is used to transmit task data, currently, without considering NAS and QoE, there is only one SRB1, so the number of SRBs is limited and the transmission efficiency of task data is low.

[0137] 2) If DRB is used to transmit task data, the base station currently transparently transmits the DRB data and forwards it to the user plane function (UPF). In other words, the base station cannot obtain the task data sent by the terminal.

[0138] Therefore, how to transmit task data information becomes a technical problem that needs to be solved urgently.

[0139] In view of this, an embodiment of the present application provides an information transmission method. In this method, a terminal can obtain first information. The first information may include a mapping relationship between first task information and first bearer information. The terminal can send data information of the first task indicated by the first task information to the base station via the first bearer indicated by the first bearer information. Based on this solution, the terminal can determine the bearer on which the data information of the task corresponding to the task information can be sent based on the mapping relationship between the task information and the bearer information. Through this mapping relationship, the terminal and the base station can support the transmission of task data information via multiple bearers, which can improve the transmission efficiency of the task data information.

[0140] Referring to FIG. 5 , which is an exemplary flowchart of an information transmission method provided in an embodiment of the present application, the method may include the following operations.

[0141] S501: The terminal obtains first information.

[0142] For example, the terminal may receive the first information from a base station. For another example, the first information may be preconfigured or predefined by a protocol. For another example, the terminal may receive the first information from a core network, such as an AMF, SMF, or UPF in a 5G system.

[0143] The first information may include a mapping relationship between the first task information and the first bearer information. The first task information may be used to describe the first task, such as including an identifier (task ID) of the first task. The first bearer information may be used to describe the first bearer, such as including one or more of an identifier (RB ID) of the first bearer, an identifier of a logical channel corresponding to the first bearer, and a type of the first bearer.

[0144] Optionally, the terminal may further obtain a mapping relationship between the second task information and the second bearer information. The second task information may be used to describe the second task, such as including an identifier of the second task. The second bearer information may be used to describe the second bearer, such as including one or more of an identifier of the second bearer, an identifier of a logical channel corresponding to the second bearer, and a type of the second bearer.

[0145] It should be noted that the mapping relationship between the first task information and the first bearer information and the mapping relationship between the second task information and the second bearer information can be indicated in the same information, that is, in the first information. Alternatively, the mapping relationship between the first task information and the first bearer information and the mapping relationship between the second task information and the second bearer information can be indicated in different information, and this application does not make specific limitations.

[0146] Herein, the type of the first bearer may include SRB, DRB, and a first type, and the first type may be a type different from SRB and DRB.

[0147] In one possible scenario, task information can correspond one-to-one with bearer information. This is illustrated by taking the example of multiple task information including the first task information and the second task information described above. For example, the first task information corresponds to the first bearer information, and the second task information corresponds to the second bearer information. In other words, the first bearer and the second bearer are different bearers. The data information of the first task indicated by the first task information is sent via the first bearer indicated by the first bearer information, and the data information of the second task indicated by the second task information is sent via the second bearer indicated by the second bearer information.

[0148] In another possible situation, multiple task information may correspond to one bearer information. Take the example of multiple task information including the above-mentioned first task information and second task information for illustration. For example, the first task information and the second task information may correspond to the first bearer information. That is to say, the aforementioned first bearer and the second bearer may be the same bearer, and the data information of the first task indicated by the first task information, and the data information of the second task indicated by the second task information are both sent through the first bearer indicated by the first bearer information. It can be understood that the first task information and the second task information are examples of multiple task information, and are not limited to only the first task information and the second task information, and there may also be third task information, etc. The description of other task information (such as the third task information, etc.) except the first task information and the second task information can refer to the first task information and the second task information. In order to avoid redundancy, they will not be repeated.

[0149] S502: The terminal sends data information of the first task to the base station.

[0150] Correspondingly, the base station receives data information of the first task from the terminal.

[0151] For example, the terminal may send data information of the first task indicated by the first task information through the first bearer indicated by the first bearer information.

[0152] In the embodiment of the present application, the first task may include data processing, AI reasoning, AI training, etc., which are not specifically limited in this application. Similarly, the data information of the first task may include the results of data processing, the results of AI reasoning, the data required for AI training, the results of AI training, the gradient information used for AI training, etc., which are not specifically limited in this application.

[0153] Based on this solution, the terminal can determine the bearer that can transmit the task data information corresponding to the task information based on the mapping relationship between the task information and the bearer information. Through this mapping relationship, the terminal and the base station can support the transmission of task data information via multiple bearers, which can improve the transmission efficiency of task data information.

[0154] In one possible implementation, when multiple task information corresponds to one bearer information, the terminal may further transmit the first task information to the base station. For example, in S502, the first task information and the second task information correspond to the first bearer information, so the data information of the first task may also include the first task information. In this way, upon receiving the task data information sent by the terminal, the base station may determine to which task the task data information belongs. Optionally, in S502, the terminal may further transmit the data information of the second task via the first bearer, and the data information of the second task may include the second task information.

[0155] It is understandable that the first bearer in S502 can be a DRB or an SRB. The following describes two cases.

[0156] Case 1: The first bearer is an SRB.

[0157] In one possible implementation, the first bearer may be an SRB. In S501, the first information may include a mapping relationship between the first task information and the first SRB information. Herein, the terminal may send task data information via multiple SRBs. For example, the terminal may send data information of the first task and data information of the second task via the first SRB, and the terminal may send data information of the third task via the second SRB.

[0158] Currently, because only SRB1 exists between connected terminals and base stations for transmitting RRC control signaling, there is no QoS guarantee mechanism. However, when terminals and base stations may need to transmit data information for multiple tasks, different SRBs are needed to provide differentiated QoS guarantees, such as those with different latency and reliability requirements.

[0159] For example, the terminal can obtain configuration information. The configuration information may include the mapping relationship between the first bearer information and the QoS information described above, such as the mapping relationship between the first SRB information and the QoS information. In this way, when the terminal sends the data information of the first task through the first bearer, it can send the data information of the first task through the first bearer according to the QoS information corresponding to the first bearer information. Optionally, the QoS information may include priority information, QoS range (parameters), aggregated maximum bit rate (AMBR), peak bit rate (PBR), etc.

[0160] Based on the above situation 1, the terminal can send data information of tasks according to different QoS through the mapping relationship between the first bearer information and the QoS information indicated by the configuration information, so that data of tasks with high latency requirements or high priority requirements can be sent first.

[0161] Case 2: The first bearer is a DRB.

[0162] In a possible implementation, the first bearer may be a DRB. In S501, the first information may include a mapping relationship between the first task information and the first DRB information.

[0163] At present, the base station directly transmits all DRBs. In order to support the data information of the DRB transmission task between the terminal and the base station, and ultimately be parsed and / or terminated by the base station, the following two methods are provided in the embodiments of the present application.

[0164] Method 1: The data information of the first task includes instruction information, indicating whether to transparently transmit the data information.

[0165] For example, the data information of the first task may include third indication information, and the third indication information may instruct the base station to transparently transmit the data information of the first task, such as the base station transparently transmits the data information of the first task to the UPF or the terminal.

[0166] For another example, the data information of the first task may include fourth indication information, and the fourth indication information may instruct the base station to parse and / or terminate the data information of the first task.

[0167] In this article, parsing can be understood as decoding, demodulating, and other operations on the task data information to obtain the task data information. Termination can be understood as not sending the task data information to other communication devices, such as core network devices or terminals.

[0168] Optionally, the third indication information and the fourth indication information can be implemented by 1-bit information. For example, when the value of the 1-bit information is 0, the base station is instructed to transparently transmit the data information of the first task, and when the value of the 1-bit information is 1, the base station is instructed to parse and / or terminate the data information of the first task. Conversely, for example, when the value of the 1-bit information is 1, the base station is instructed to transparently transmit the data information of the first task, and when the value of the 1-bit information is 0, the base station is instructed to parse and / or terminate the data information of the first task.

[0169] In another embodiment, the indication information may be implicit indication information. For example, it may be implicitly indicated by whether the DRB has the SDAP layer information. Since the DRB carrying the task data information does not have the SDAP layer, and the DRB carrying other data information, such as user Internet access data, has the SDAP layer. Therefore, if the first bearer contains SDAP layer information, such as an SDAP header, it can be considered that the first bearer carries other data information, and the base station can transparently transmit the other data information. If the first bearer does not contain SDAP layer information, then it can be considered that the first bearer carries the task data information, and the base station can parse and / or terminate the task data information.

[0170] Optionally, the implicit indication information can also be implicitly indicated by whether the DRB has information from other layers or the task resource data (TRD) layer. The TRD layer can be the protocol layer provided in this document, which is used to process the first AI model of the first task, as described later.

[0171] Assume that both the DRB carrying task data information and the DRB carrying other data information have SDAP layer information. However, the aforementioned indication information is added to the SDAP layer, the PDCP layer, or a layer above SDAP to indicate whether the information carried by the DRB is transparently transmitted. In other words, even if the DRB for other data information also has SDAP layer information, an explicit indication information can be used to indicate that it is the DRB for task data information.

[0172] In the above scheme, the indication information can indicate which DRBs carry the data information of the task and which DRBs carry other data information, avoiding the situation where the base station cannot know which DRBs carry the data information of the task and which DRBs carry other data information by only parsing the DRB identifier. The indication information also indicates whether the data information needs to be transparently transmitted, parsed or terminated by the base station.

[0173] Based on the above solution, the indication information indicates whether the data information of the task is parsed and / or terminated by the base station, thereby achieving the DRB reachability to the base station, so that the base station can obtain the data information of the task.

[0174] Method 2:

[0175] The base station can configure a dedicated DRB for the data information of the task. For example, in S501, the first bearer information can be the information of the DRB configured by the base station for the terminal specifically for carrying the data information of the first task. In this way, since the data information of the task and other data information do not share the DRB, different DRB attributes have been determined before the base station configures the DRB for the terminal. Therefore, the terminal can send the data information of the first task on the corresponding DRB based on the first information.

[0176] The base station can obtain DRB information and then know whether the DRB carries task data information or other data information, and then perform differentiated processing of parsing and transparent transmission. For example, the base station can transparently transmit other data information, parse and / or terminate the task data information.

[0177] Based on the above solution, the base station can configure DRB for the data information of the task to make the DRB reachable to the base station, so that the base station can obtain the data information of the task carried by the DRB.

[0178] In one possible implementation, SRB and DRB share LCID. For example, referring to FIG6 , a format of a MAC subheader is shown. The MAC subheader in FIG6 may be composed of one or more of an R field, an F field, an LCID, an extended LCID (eLCID), and an L field. Among them, the LCID may be used to indicate a logical channel. The extended LCID may also be used to indicate a logical channel. The L field may represent a length field, which may indicate the number of bytes of the MAC SDU contained in the MAC sub-PDU or the number of bytes of the MAC control element (CE) contained in the MAC sub-PDU. The F field may represent a format field, indicating the size of the aforementioned L field. The R field may be a reserved field, for example, it may be set to 0.

[0179] The MAC subheader may carry data information for the first task. The LCID is 6 bits long. LCID=0 is reserved for SRB0, and the LCID numbers for the remaining SRBs and DRBs are integers between 1 and 32. For example, the LCID in the MAC sub-protocol data unit (subPDU) carrying data information for the first task sent by the terminal in S502 may be an integer between 1 and 32.

[0180] In another possible implementation, SRB and DRB may not share LCIDs. That is, the LCID when the first bearer is an SRB is different from the LCID when the first bearer is a DRB. Based on this solution, since the number of LCIDs shared by SRB and DRB is 32, if multiple SRBs are supported to transmit task data information, the number of DRB LCIDs will be excessive. Therefore, independent LCIDs can be set for SRB and DRB.

[0181] Optionally, the MAC subheader may be enhanced herein. As shown in Figure 6, the R field may indicate that the first bearer is an SRB or a DRB. For example, when the value of the R field is 0, it may indicate that the first bearer is an SRB, and when the value of the R field is 1, it may indicate that the first bearer is a DRB. Conversely, when the value of the R field is 1, it may indicate that the first bearer is an SRB, and when the value of the R field is 0, it may indicate that the first bearer is a DRB.

[0182] In one example, the PDCP layer currently limits the maximum number of concatenated data packets to 16, with a maximum data size of 9KB per data packet. Therefore, it cannot carry very large models or data. In this context, the RRC layer supports concatenation, for example, through a secondary node (SN). In this context, the maximum number of SNs supported can be greater than 16. This allows the terminal to send very large models or data to the base station.

[0183] It is understood that the concatenation mentioned above can be understood as combining multiple data packets into a larger data packet. The multiple data packets may be obtained by segmenting a single data packet and then performing some operations such as encoding or modulation. Alternatively, the multiple data packets may come from different data, such as data information for different tasks.

[0184] Optionally, the embodiment shown in FIG5 may further include the following operation S503.

[0185] S503: The terminal processes the first AI model.

[0186] For example, the terminal may process the first AI model used to perform the first task. The data information of the first task in S502 may include a processing result of the terminal processing the first AI model.

[0187] In one possible implementation, the terminal may process the first AI model according to the configuration of the base station. The base station may configure the bearer information or the task information. For example, the base station may send first configuration information to the terminal, where the first configuration information may include a mapping relationship between the first task information and the processing method of the AI ​​model. The terminal may process the first AI model of the first task according to the processing method corresponding to the first task information.

[0188] Alternatively, the first configuration information may include a mapping relationship between the first bearer information and the processing method of the AI ​​model. The terminal may process the first AI model of the first task according to the processing method corresponding to the first bearer information.

[0189] Currently, the RRC layer does not support AI model processing. Therefore, this functionality can be newly defined in the RRC layer, or a new layer can be added above or below the RRC layer to support AI model processing. Optionally, a new layer can be added to the user plane protocol stack to support AI model processing. As shown in Figure 7, a TRD layer is added above the SDAP layer.

[0190] In this article, AI model processing methods may include one or more of model compression, model pruning, model security, model privacy, reasoning, data processing, and model training.

[0191] Based on the above solution, by adding a new layer or defining a new function in the RRC layer, the function of processing the AI ​​model is realized for processing the AI ​​model.

[0192] Optionally, the base station may configure the switch and parameters of the processing mode of the AI ​​model. For example, the first configuration information may include the switch configuration of the processing mode of the AI ​​model and / or the parameter configuration of the processing mode of the AI ​​model. The switch configuration of the processing mode may include on or off. When the switch configuration of the processing mode includes on, the terminal is instructed to process the AI ​​model according to the processing mode. When the switch configuration of the processing mode includes off, the terminal is instructed not to perform corresponding processing on the AI ​​model.

[0193] It is understandable that the parameter configuration may include the parameters required for the terminal to process the AI ​​model. For example, when the processing method includes model training, the parameter configuration may include the parameters used by the terminal to perform model training. For another example, when the processing method includes inference, the parameter configuration may include the input parameters used by the terminal to perform inference. For another example, when the processing method includes model pruning, the parameter configuration may include the location to be pruned or the size of the pruned model. For another example, when the processing method includes model compression, the parameter configuration may include one or more of the following: the model compression method, the algorithm identifier, and the model compression parameters.

[0194] In one possible scenario, when processing an AI model, the terminal may process the AI ​​model in a pre-configured format. For example, if the processing method includes model compression, the terminal may process the AI ​​model according to a pre-set compression algorithm. For another example, if the processing method includes data processing, the terminal may process the data in a pre-set format.

[0195] Optionally, to enhance flexibility, the terminal can flexibly select a format to process the AI ​​model based on changes in its environment, such as location, channel conditions, and signal strength. Therefore, the terminal can send format information to the base station, that is, the format information used when processing the AI ​​model. For example, the terminal can carry the above format information in the data information of the first task.

[0196] In one possible implementation, the data information of the first task may carry routing information. The routing information may indicate a node that parses and / or terminates the data information of the first task. The node may include a node of a core network device, such as an access mobile management function (AMF), a session management function (SMF), a UPF, etc., and may also include a node of a base station, such as a centralized unit (CU), a distributed unit (DU), a centralized control plane (CU control plane, CU-CP) or a centralized user plane (CU user plane, CU-UP), etc. Based on this solution, the base station may determine the node that parses and / or terminates the data information of the first task according to the routing information in the data information of the first task, and forward the data information of the first task to the corresponding node.

[0197] For example, the data information of the first task may include one or more of a node type, a node identifier, first bearer information, and first task information. The node type, node identifier, one or more of the first bearer information, and first task information may indicate a node that parses and / or terminates the data information of the first task. The first bearer information and / or the first task information may have a mapping relationship with a node, so the node that parses and / or terminates the data information of the first task may be determined through the mapping relationship between the first bearer information and the node and / or the mapping relationship between the first task information and the node.

[0198] It can be understood that the mapping relationship between the first bearer information and the node, and / or the mapping relationship between the first task information and the node in this article can be a base station, such as RAN, CU, DU, CU-CP or CU-UP, or a core network device, such as AMF, UPF or SMF, indicated to the terminal. For example, the base station or the core network device can send third configuration information to the terminal. The third configuration information may include the mapping relationship between the first bearer information and the node. And / or, the third configuration information may include the mapping relationship between the first task information and the node. In this way, the terminal can understand the node that parses and / or terminates the data information of the first task, and carry the data information of the first task on the first bearer indicated by the corresponding first bearer information. Optionally, the above mapping relationship can also be pre-configured to the terminal without the need for signaling transmission.

[0199] Optionally, each node in this document may receive fourth configuration information, which may include a mapping relationship between the first bearer information and the node, and / or the fourth configuration information may include a mapping relationship between the first task information and the node. The fourth configuration information may be sent by a node of the base station to each node, such as RAN to CU, DU, CU-CP, CU-UP or core network equipment, such as AMF, UPF or SMF. Or it may be a core network device, such as AMF to UPF, SMF, RAN, CU, DU, CU-CP or CU-UP. In this document, there is no specific limitation on the node that sends the fourth configuration information.

[0200] The following explains and illustrates routing information through different examples.

[0201] Example 1:

[0202] 5G supports CU / DU split deployment scenarios. The CU is typically deployed in a centralized cloud configuration, facilitating resource sharing, while the DU is deployed at the edge, closer to the service end and offering the advantage of low latency. Numerous CU / DU splitting methods have been discussed in the 5G protocol, but ultimately, only the standardized solution has been adopted: deploying the CU at the PDCP layer and above, and the DU at the RLC layer and below, as shown in Figure 8.

[0203] Based on the above CU / DU split protocol stack, it can be seen that the protocol layers between the terminal and DU include PHY, MAC, and RLC, and the protocol layers between the terminal and CU include PDCP, RRC, PDCP, SDAP, etc. Therefore, the terminal and DU can communicate in the following ways:

[0204] Mode 1: Carrying the data through SRB. That is, the first bearer is SRB.

[0205] For example, the terminal may send the data information of the first task to the CU through the SRB, and the CU may forward the data information of the first task to the DU.

[0206] For example, the terminal sends the data information of the first task to the CU through the TRC layer. After receiving it, the CU parses it and finds out that it needs to be forwarded to the DU, and forwards the message through the interface between the CU and the DU (such as the F1 interface in 5G).

[0207] It is understandable that the CU uses the following information to identify which data information of the first task needs to be forwarded to the DU:

[0208] Explicit method

[0209] For example, the data information of the first task explicitly carries a node identifier and / or node type, that is, the identifier and / or node type of the DU is DU. In this way, after receiving the first bearer, the CU can determine whether to forward the data to the DU based on the node identifier and / or node type carried in the data information of the first task.

[0210] Implicit method

[0211] For example, the data information of the first task may carry the first task information and / or the first bearer information, and the CU may identify whether it needs to be forwarded to the DU based on the first task information and / or the first bearer information. For example, when the data information of the first task carries the first task information, the CU may determine whether it needs to be forwarded to the DU based on the mapping relationship between the first task information and the node. For another example, when the data information of the first task carries the first bearer information, the CU may determine whether it needs to be forwarded to the DU based on the mapping relationship between the first bearer information and the node.

[0212] It can be understood that the above method 1 introduces the method for the CU to determine whether to forward the data information of the first task to the DU. The method for the CU to determine whether to forward the data information of the first task to other nodes, such as AMF, UPF or SMF, can also be implemented with reference to method 1. Similarly, other nodes, such as DU, core network equipment, CU-CP or CU-UP can also refer to method 1 to determine whether the data information of the first task needs to be forwarded.

[0213] Method 2: Carrying through TRS / PHY.

[0214] 9 , the data information of the first task is carried by DCI, UCI or MAC CE, and the DU can parse and process the DCI, UCI or MAC CE.

[0215] Mode 3: Through DRB or SRB bearer. That is, the first bearer is DRB or SRB.

[0216] In this article, the DU can be enhanced to enable it to fully support the aforementioned task data information transmission via DRB and / or SRB. In this way, when the DU recognizes that the data information of the first task is sent to it by the terminal, it does not need to be forwarded to the CU and then forwarded to the DU by the CU.

[0217] Referring to Figure 10, the terminal can perform the first task through the TRD layer and send the data information of the first task to the DU through the DRB or SRB. The DU shown in Figure 10 may be an enhanced DU. The DU can determine path 1 based on the first bearer information and / or first task information carried in the data information of the first task, that is, the DU parses and / or terminates the data information of the first task. Alternatively, path 2 can be determined, that is, forwarded by the DU to the CU-CP. Alternatively, path 3 or path 4 can be determined, that is, forwarded by the DU to the CU-CP.

[0218] Example 2:

[0219] For centrally deployed CUs, the 5G standard supports further segmentation of the CU into the CU-CP and CU-UP to support independent deployment and upgrades of the CU-CP and CU-UP. The CU-CP is responsible for the control signaling corresponding to the air interface control plane protocol stack, such as the PDCP and RRC layers; the CP-UP is responsible for the data portion of the air interface user plane protocol stack, such as the PDCP and SDAP layers.

[0220] There are two ways to exchange task data between the terminal and CU-CP:

[0221] Mode 1: Carrying the data through SRB. That is, the first bearer is SRB.

[0222] This can be implemented by referring to Method 1 in Example 1.

[0223] Mode 2: Through DRB bearer. That is, the first bearer is DRB.

[0224] Since the current CU-CP of 5G only has SRB bearer, it is possible to enhance the CU-CP as in the DU in Example 1, so that the CU-CP can integrate the data information of the task transmitted through DRB.

[0225] Referring to Figure 10, the terminal can perform the first task through the TRD layer, and can send the data information of the first task to the DU through the DRB or SRB. The DU shown in Figure 10 can determine path 1 based on the first bearer information and / or first task information carried in the data information of the first task, that is, the data information of the first task is parsed and / or terminated by the DU. Alternatively, path 2 can also be determined, that is, forwarded by the DU to the CU-CP. The CU-CP shown in Figure 10 can be an enhanced CU-CP. The CU-CP determines that the data information of the first task is parsed and / or terminated by the CU-CP based on the first bearer information and / or first task information carried in the data information of the first task. Alternatively, path 3 or path 4 can also be determined, that is, forwarded by the DU to the CU-CP.

[0226] Example 3:

[0227] There are two ways for the terminal to interact with CU-UP for task data information:

[0228] Mode 1: Carrying the data through SRB. That is, the first bearer is SRB.

[0229] Since the CU-CP currently only has DRBs, the CU-UP can be enhanced to enable it to transmit task data information via SRBs. The enhanced CU-UP can be implemented by referring to Method 1 in Example 1.

[0230] Mode 2: Through DRB bearer. That is, the first bearer is DRB.

[0231] Since 5G's current CU-UP already has DRB bearer, it is possible to enhance CU-UP, just like the DU in Example 1, so that CU-UP can integrate the ability to transmit data information of tasks through DRB.

[0232] Referring to Figure 10, the terminal can perform the first task through the TRD layer, and can send the data information of the first task to the DU through the DRB or SRB. The DU shown in Figure 10 can determine path 1 based on the first bearer information and / or first task information carried in the data information of the first task, that is, the data information of the first task is parsed and / or terminated by the DU. Alternatively, path 2 can also be determined, that is, forwarded by the DU to the CU-CP. Alternatively, path 3 or path 4 can also be determined, that is, forwarded by the DU to the CU-CP. The CU-UP shown in Figure 10 can be an enhanced CU-UP. The CU-UP determines that the data information of the first task is parsed and / or terminated by the CU-UP based on the first bearer information and / or first task information carried in the data information of the first task.

[0233] The following describes the communication device used to implement the above method in the embodiment of the present application with reference to the accompanying drawings. Therefore, the above contents can be used in subsequent embodiments, and repeated contents will not be repeated.

[0234] Figure 11 is a schematic block diagram of a communication device 1100 provided in an embodiment of the present application. The communication device 1100 can implement the functions or steps implemented by the terminal device or network device in the above-mentioned various method embodiments. The communication device may include a processing unit 1110 and a transceiver unit 1120. Optionally, it may also include a storage unit, which can be used to store instructions (codes or programs) and / or data. The processing unit 1110 and the transceiver unit 1120 can be coupled to the storage unit. For example, the processing unit 1110 can read the instructions (codes or programs) and / or data in the storage unit to implement the corresponding method. The above-mentioned units can be set independently or partially or fully integrated.

[0235] In some possible implementations, the communication device 1100 can implement the behaviors and functions of the terminal device in the above-mentioned method embodiments. For example, the communication device 1100 can be a terminal device, or a component (such as a chip or circuit) used in a terminal device. The transceiver unit 1120 can be used to perform all receiving or sending operations performed by the terminal device in the embodiment shown in Figure 5. For example, S502 in the embodiment shown in Figure 5, and / or other processes for supporting the technology described herein; wherein the processing unit 1110 is used to perform all operations except the receiving and sending operations performed by the terminal device in the embodiment shown in Figure 5. For example, S501 in the embodiment shown in Figure 5, and / or other processes for supporting the technology described herein.

[0236] For example, the processing unit 1110 is configured to obtain first information including a mapping relationship between first task information and first bearer information. The transceiver unit 1120 is configured to send data information of the first task indicated by the first task information to the network device via the first bearer indicated by the first bearer information.

[0237] In some possible implementations, the communication device 1100 can implement the behaviors and functions of the network device in the above-mentioned method embodiments. For example, the communication device 1100 can be a network device, or a component (such as a chip or circuit) used in a network device. The transceiver unit 1120 can be used to perform all receiving or sending operations performed by the network device in the embodiment shown in Figure 5. For example, S502 in the embodiment shown in Figure 5, and / or other processes for supporting the technology described herein; wherein the processing unit 1110 is used to perform all operations except the sending and receiving operations performed by the network device in the embodiment shown in Figure 5.

[0238] For example, processing unit 1110 is configured to generate first information. Transceiver unit 1120 is configured to send the first information to a terminal device, where the first information includes a mapping relationship between first task information and first bearer information. Transceiver unit 1120 is further configured to receive data information of the first task indicated by the first task information from the terminal device via the first bearer indicated by the first bearer information.

[0239] For the operations performed by the processing unit 1110 and the transceiver unit 1120 , please refer to the relevant description of the aforementioned method embodiment.

[0240] It should be understood that the processing unit 1110 in the embodiment of the present application can be implemented by a processor or a processor-related circuit component, and the transceiver unit 1120 can be implemented by a transceiver or a transceiver-related circuit component or a communication interface.

[0241] Based on the same concept, as shown in FIG12 , an embodiment of the present application provides a communication device 1200. The communication device 1200 includes a processor 1210. Optionally, the communication device 1200 may further include a memory 1220 for storing instructions executed by the processor 1210, or storing input data required by the processor 1210 to execute instructions, or storing data generated after the processor 1210 executes instructions. The processor 1210 can implement the method shown in the above method embodiment through the instructions stored in the memory 1220.

[0242] Based on the same concept, as shown in Figure 13, an embodiment of the present application provides a communication device 1300, which can be a chip or a chip system. Optionally, in the embodiment of the present application, the chip system can be composed of a chip, or can include a chip and other discrete devices.

[0243] Communication device 1300 may include at least one processor 1310, coupled to a memory. Optionally, the memory may be located within or outside the device. For example, communication device 1300 may also include at least one memory 1320. Memory 1320 stores the necessary computer programs, configuration information, computer programs or instructions, and / or data for implementing any of the aforementioned embodiments. Processor 1310 may execute the computer programs stored in memory 1320 to perform the method in any of the aforementioned embodiments.

[0244] The coupling in the embodiments of the present application is an indirect coupling or communication connection between devices, units, or modules, which can be electrical, mechanical, or other forms, and is used for information exchange between devices, units, or modules. The processor 1310 may operate in conjunction with the memory 1320. The specific connection medium between the transceiver 1330, processor 1310, and memory 1320 is not limited in the embodiments of the present application.

[0245] The communication device 1300 may also include a transceiver 1330, and the communication device 1300 can exchange information with other devices through the transceiver 1330. The transceiver 1330 can be a circuit, a bus, a transceiver or any other device that can be used for information exchange, or is called a signal transceiver unit. As shown in Figure 13, the transceiver 1330 includes a transmitter 1331, a receiver 1332 and an antenna 1333. In addition, when the communication device 1300 is a chip-type device or circuit, the transceiver in the communication device 1300 can also be an input and output circuit and / or a communication interface, which can input data (or receive data) and output data (or send data). The processor is an integrated processor or microprocessor or integrated circuit, and the processor can determine the output data based on the input data.

[0246] In one possible implementation, the communication device 1300 can be applied to a terminal device. Specifically, the communication device 1300 can be a terminal device or a device that can support the terminal device in implementing the functions of the terminal device in any of the above-mentioned embodiments. The memory 1320 stores the necessary computer programs, computer programs or instructions and / or data to implement the functions of the terminal device in any of the above-mentioned embodiments. The processor 1310 can execute the computer program stored in the memory 1320 to perform the method performed by the terminal device in any of the above-mentioned embodiments.

[0247] In one possible implementation, the communication device 1300 can be applied to a network device. Specifically, the communication device 1300 can be a network device, or a device that can support the network device in implementing the functions of the network device in any of the above-mentioned embodiments. The memory 1320 stores the necessary computer programs, computer programs, instructions, and / or data to implement the functions of the network device in any of the above-mentioned embodiments. The processor 1310 can execute the computer program stored in the memory 1320 to perform the method performed by the network device in any of the above-mentioned embodiments.

[0248] Since the communication device 1300 provided in this embodiment can be applied to a network device to implement the method executed by the above-mentioned network device, or can be applied to a terminal device to implement the method executed by the above-mentioned terminal device, the technical effects that can be obtained can be referred to the above-mentioned method embodiments and will not be repeated here.

[0249] In the embodiments of the present application, the processor may be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, and may implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present application. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present application may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0250] In an embodiment of the present application, the memory may be a non-volatile memory, such as a hard disk drive (HDD) or a solid-state drive (SSD), etc., or a volatile memory (volatile memory), such as a random-access memory (RAM). The memory may also be any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory in an embodiment of the present application may also be a circuit or any other device that can implement a storage function, for storing computer programs, computer programs or instructions and / or data.

[0251] Based on the above embodiments, referring to FIG14 , an embodiment of the present application also provides another communication device 1400, including: an input / output interface 1410 and a logic circuit 1420; the input / output interface 1410 is used to receive code instructions and transmit them to the logic circuit 1420; the logic circuit 1420 is used to run code instructions to execute the method executed by the network device or terminal device in any of the above embodiments.

[0252] The following describes in detail the operations performed by the communication device when applied to a network device or a terminal device.

[0253] In an optional implementation, the communication device 1400 may be applied to a network device to execute the method executed by the aforementioned network device, for example, the method executed by the network device in the embodiment shown in FIG. 5 .

[0254] Logic circuit 1420 is configured to generate first information. Input / output interface 1410 is configured to output the first information to a terminal device, the first information including a mapping relationship between first task information and first bearer information. Input / output interface 1410 is further configured to input data information of the first task indicated by the first task information from the terminal device via a first bearer indicated by the first bearer information.

[0255] Since the communication device 1400 provided in this embodiment can be applied to a network device to implement the method executed by the above network device, the technical effects that can be obtained can be referred to the above method embodiment and will not be described in detail here.

[0256] In an optional implementation, the communication device 1400 may be applied to a terminal device to execute the method executed by the aforementioned terminal device, for example, the method executed by the terminal device in the embodiment shown in FIG. 5 .

[0257] The logic circuit 1420 is configured to obtain first information including a mapping relationship between first task information and first bearer information. The input / output interface 1410 is configured to output data information of the first task indicated by the first task information to the network device via the first bearer indicated by the first bearer information.

[0258] Since the communication device 1400 provided in this embodiment can be applied to a terminal device to implement the method executed by the terminal device, the technical effects that can be obtained can be referred to the above method embodiment and will not be described in detail here.

[0259] Based on the above embodiments, embodiments of the present application further provide a communication system. The communication system includes at least one communication device applied to a network device and at least one communication device applied to a terminal device. The technical effects that can be achieved can be referenced to the above method embodiments and will not be further described here.

[0260] Based on the above embodiments, embodiments of the present application further provide a computer-readable storage medium storing a computer program or instruction. When the instruction is executed, the method executed by the network device or the method executed by the terminal device in any of the above embodiments is implemented. The computer-readable storage medium may include various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory, a random access memory, a magnetic disk, or an optical disk.

[0261] To implement the functions of the communication device shown in Figures 11 to 14 above, embodiments of the present application further provide a chip including a processor for supporting the communication device in implementing the functions of the network device or terminal device in the above method embodiments. In one possible design, the chip is connected to or includes a memory, which is used to store computer programs, instructions, and data necessary for the communication device.

[0262] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0263] The present application is described with reference to the flow chart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present application. It should be understood that each flow process and / or box in the flow chart and / or block diagram and the combination of the flow process and / or box in the flow chart and / or block diagram can be realized by a computer program or instruction. These computer programs or instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processing machine or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for realizing the function specified in one flow chart flow or multiple flows and / or one box or multiple boxes of the block diagram.

[0264] These computer programs or instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0265] These computer programs or instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0266] It should be understood that the term "and / or" as used herein is merely a description of an association relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the symbol " / " used in this application can represent "and / or," for example, A / B represents A and / or B.

[0267] It should be understood that in the embodiments of the present application, "B corresponding to A" means that B is associated with A and B can be determined based on A. However, it should also be understood that determining B based on A does not mean determining B based solely on A, but B can also be determined based on A and / or other information.

[0268] The term "plurality" used in the embodiments of the present application refers to two or more.

[0269] The first, second, etc. descriptions appearing in the embodiments of this application are only used for illustration and distinction of the described objects. There is no order, nor does it indicate a special limitation on the number of described objects in the embodiments of this application, and cannot constitute any limitation on the embodiments of this application.

[0270] The contents of the various embodiments of this application can refer to each other. If there is no special explanation and logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other. The technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0271] It is understood that in the embodiments of the present application, the terminal device and / or the network device may perform some or all of the steps in the embodiments of the present application. These steps or operations are merely examples. In the embodiments of the present application, other operations or variations of various operations may also be performed. In addition, the various steps may be performed in a different order than those presented in the embodiments of the present application, and it is possible that not all of the operations in the embodiments of the present application need to be performed.

Claims

1. An information transmission method, characterized in that: include: Acquire first information, where the first information includes a mapping relationship between first task information and first bearer information; The data information of the first task indicated by the first task information is sent to the network device through the first bearer indicated by the first bearer information.

2. The method according to claim 1, characterized in that The first information further includes a mapping relationship between second task information and the first bearer information; the first task information is different from the second task information; The data information of the first task also includes the first task information.

3. The method according to claim 1 or 2, characterized in that Also includes: The first AI model used to perform the first task is processed; the data information of the first task also includes a processing result of the first AI model.

4. The method according to claim 3, characterized in that Also includes: receiving first configuration information from the network device, where the first configuration information includes a mapping relationship between the first task information and a processing method of the AI ​​model or a mapping relationship between the first bearer information and a processing method of the AI ​​model; The processing of the first AI model for performing the first task includes: Processing the first AI model according to the processing method of the AI ​​model corresponding to the first task information; or The processing method of the AI ​​model is processed according to the processing method of the AI ​​model corresponding to the first bearer information.

5. The method according to claim 4, characterized in that The processing method of the AI ​​model includes: switch configuration of the AI ​​model and / or parameter configuration of the AI ​​model; The switch configuration of the AI ​​model includes on or off; when the switch configuration of the AI ​​model is on, the switch configuration of the AI ​​model is used to indicate that the first AI model is processed; when the switch configuration of the AI ​​model is off, the switch configuration of the AI ​​model is used to indicate that the first AI model is not processed.

6. The method according to claim 4 or 5, characterized in that The processing method of the AI ​​model includes: switch configuration and / or parameter configuration of one or more of model compression, model pruning, model security, model privacy, reasoning, data processing and training.

7. The method according to any one of claims 3 to 6, characterized in that: The data information of the first task further includes format information, and the format information is used to indicate the format of the processing method.

8. The method according to any one of claims 1 to 7, characterized in that: The first bearer information includes one or more of the type of the first bearer, the identifier of the first bearer, and the logical channel identifier LCID of the first bearer.

9. The method according to any one of claims 1 to 8, characterized in that: The data information of the first task includes first indication information, where the first indication information is used to indicate that the first bearer is a signaling bearer; or The data information of the first task includes second indication information, where the second indication information is used to indicate that the first bearer is a data bearer.

10. The method according to any one of claims 1 to 9, characterized in that: Also includes: Acquire second configuration information, where the second configuration information includes a mapping relationship between the first bearer information and quality of service (QoS) information; The sending, through the first bearer indicated by the first bearer information, data information of the first task indicated by the first task information to the network device, includes: According to the QoS information corresponding to the first bearer information, data information of the first task indicated by the first task information is sent to the network device through the first bearer indicated by the first bearer information, where the first bearer is a signaling bearer.

11. The method according to any one of claims 1 to 10, characterized in that: The first bearer is a signaling bearer or a data bearer, and the LCID of the signaling bearer is different from the LCID of the data bearer.

12. The method according to any one of claims 1 to 8, characterized in that: The data information of the first task includes third indication information, and the third indication information instructs the network device to transparently transmit the data information of the first task, and the first bearer is a data bearer; or The data information of the first task includes fourth indication information, and the fourth indication information instructs the network device to terminate the data information of the first task. The first bearer is a data bearer.

13. The method according to any one of claims 1 to 8, characterized in that: The data information of the first task further includes one or more items of information included in the first bearer information and / or one or more items of information included in the first task information; Among them, one or more items of information included in the first bearer information and / or one or more items of information included in the first task information are used to indicate whether the network device terminates the first bearer, and the first bearer is a data bearer.

14. The method according to any one of claims 1 to 13, characterized in that: The data information of the first task also includes a node type, a node identifier, one or more of the first bearer information and the first task information, and the node type, the node identifier, the first bearer information and the first task information are used to indicate the node that terminates the data information of the first task.

15. The method according to any one of claims 1 to 14, characterized in that: Also includes: Obtain third configuration information, where the third configuration information includes a mapping relationship between the first bearer information and a node, where the node is used to terminate the first bearer; And / or, the third configuration information includes a mapping relationship between the first task information and a node, and the node is used to terminate the first bearer.

16. An information transmission method, characterized in that: include: Sending first information to the terminal device, where the first information includes a mapping relationship between the first task information and the first bearer information; Receive data information of the first task indicated by the first task information from the terminal device through the first bearer indicated by the first bearer information.

17. The method according to claim 16, characterized in that The first information further includes a mapping relationship between second task information and the first bearer information; the first task information is different from the second task information; The data information of the first task also includes the first task information.

18. The method according to claim 16 or 17, characterized in that The data information of the first task also includes a processing result of the terminal device processing the first AI model used to execute the first task.

19. The method according to claim 18, characterized in that Also includes: Send first configuration information to the terminal device, where the first configuration information includes a mapping relationship between the first task information and the processing method of the AI ​​model, or a mapping relationship between the first bearer information and the processing method of the AI ​​model.

20. The method according to claim 19, wherein The processing method of the AI ​​model includes: switch configuration of the AI ​​model and / or parameter configuration of the AI ​​model; The switch configuration of the AI ​​model includes on or off; when the switch configuration of the AI ​​model is on, the switch configuration of the AI ​​model is used to indicate that the first AI model is processed; when the switch configuration of the AI ​​model is off, the switch configuration of the AI ​​model is used to indicate that the first AI model is not processed.

21. The method according to claim 19 or 20, characterized in that The processing method of the AI ​​model includes: switch configuration and / or parameter configuration of one or more of model compression, model pruning, model security, model privacy, reasoning, data processing and training.

22. The method according to any one of claims 18 to 21, characterized in that: The data information of the first task further includes format information, and the format information is used to indicate the format of the processing method.

23. The method according to any one of claims 16 to 22, characterized in that: The first bearer information includes one or more of the type of the first bearer, the identifier of the first bearer, and the logical channel identifier LCID of the first bearer.

24. The method according to any one of claims 16 to 23, characterized in that: The data information of the first task includes first indication information, where the first indication information is used to indicate that the first bearer is a signaling bearer; or The data information of the first task includes second indication information, where the second indication information is used to indicate that the first bearer is a data bearer.

25. The method according to any one of claims 16 to 24, characterized in that: Also includes: Send second configuration information to the terminal device, where the second configuration information includes a mapping relationship between the first bearer information and quality of service QoS information.

26. The method according to any one of claims 16 to 23, characterized in that: The first bearer is a signaling bearer or a data bearer, and a logical channel identifier LCID of the signaling bearer is different from an LCID of the data bearer.

27. The method according to any one of claims 16 to 23, characterized in that: The data information of the first task includes third indication information, and the third indication information instructs the network device to transparently transmit the data information of the first task, and the first bearer is a data bearer; or The data information of the first task includes fourth indication information, and the fourth indication information instructs the network device to terminate the data information of the first task. The first bearer is a data bearer.

28. The method according to any one of claims 16 to 23, characterized in that: The data information of the first task further includes one or more items of information included in the first bearer information and / or one or more items of information included in the first task information; Among them, one or more items of information included in the first bearer information and / or one or more items of information included in the first task information are used to indicate whether the network device terminates the first bearer, and the first bearer is a data bearer.

29. The method according to any one of claims 16 to 27, characterized in that: The data information of the first task also includes a node type, a node identifier, one or more of the first bearer information and the first task information, and the node type, the node identifier, the first bearer information and the first task information are used to indicate the node that terminates the data information of the first task.

30. The method according to any one of claims 16 to 29, characterized in that: Also includes: Send third configuration information to the terminal device, the third configuration information including a mapping relationship between the first bearer information and a node, the node being used to terminate the first bearer; and / or the third configuration information including a mapping relationship between the first task information and a node, the node being used to terminate the first bearer.

31. The method according to any one of claims 16 to 30, characterized in that: Also includes: Send fourth configuration information to each node, the fourth configuration information including the mapping relationship between the first bearer information and the node, the node is used to terminate the first bearer; and / or, the fourth configuration information including the mapping relationship between the first task information and the node, the node is used to terminate the first bearer.

32. A communication device, characterized in that: The method comprises means for performing the method according to any one of claims 1 to 15.

33. A communication device, characterized in that: The method comprises means for executing the method according to any one of claims 16 to 31.

34. A communication device, characterized in that: include: processor and memory; The memory is used to store computer programs or instructions; The processor is configured to execute a computer program or instruction in a memory, causing the apparatus to perform the method according to any one of claims 1 to 15, or causing the apparatus to perform the method according to any one of claims 16 to 31.

35. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which, when called by an electronic device, enable the electronic device to execute the method according to any one of claims 1 to 15, or enable the electronic device to execute the method according to any one of claims 16 to 31.

36. A computer program product, characterized in that The method comprises computer-executable instructions, which, when executed on a computer, enable the computer to execute the method according to any one of claims 1 to 15, or enable the electronic device to execute the method according to any one of claims 16 to 31.

Images