Communication method and communication apparatus

Abstract

The application provides a communication method and a communication device. The method comprises: obtaining, from a second communication device, configuration information related to data collection of a first communication device, or a training data set or model parameters of the second communication device side, the training data set being used for training an AI model of the second communication device, and the model parameters comprising parameters of the AI model after model training; and in a case where it is determined that the configuration information or the training data set or the model parameters sent by the second communication device are lost, sending, to the second communication device, a second request message for obtaining complete configuration information related to data collection of the first communication device or the training data set or the model parameters of the second communication device side according to first information, the first information indicating a number of times and / or time information of sending the second request message. By sending the second request message according to the first information, signaling overhead and transmission load can be reduced.

Description

Technical Field

[0001] This application relates to the field of communication technology, and more specifically, to a communication method and a communication device. Background Technology

[0002] Currently, artificial intelligence (AI) has been introduced into wireless communication networks and has been widely applied in many application scenarios of air interface technology, such as AI-based channel state information (CSI) feedback, AI-based beam management, and AI-based positioning, playing an increasingly important role.

[0003] In scenarios combining AI and wireless communication technologies, AI models can be deployed on the network side and / or the terminal side for training and updating. After the AI ​​model training is complete, each device can perform inference based on the trained AI model. When deploying the AI ​​model on the terminal side, the terminal device can obtain configuration data for data collection, training datasets, or model parameters from the network side to obtain the desired AI model. In this case, how the terminal device can flexibly obtain data from the network side (e.g., configuration data, training datasets, or model parameters used by the UE to obtain measurement results) is a problem that needs to be considered. Summary of the Invention

[0004] This application provides a communication method and a communication device that enables terminal devices to flexibly obtain configurations or data related to AI models from the network side, thereby reducing signaling overhead or transmission load.

[0005] In a first aspect, a communication method is provided, which can be executed by a first communication device, which can be a terminal device, or a component of the terminal device (such as a chip or circuit), without limitation.

[0006] The method includes: sending a first request message to a second communication device, the first request message being used to request relevant configuration information for data collection by the first communication device, or the first request message being used to request training datasets or model parameters on the second communication device side, the training dataset including datasets used by the second communication device side to train artificial intelligence (AI) models, the model parameters including parameters of the AI ​​model after model training; receiving first configuration information or first data from the second communication device, the first configuration information including relevant configuration information for data collection by the first communication device, the first data including training datasets or model parameters on the second communication device side; and, if it is determined that the first configuration information or the first data is lost, sending a second request message to the second communication device according to first information, the second request message being used to obtain complete relevant configuration information for data collection by the first communication device or training datasets or model parameters on the second communication device side, the first information indicating the number of times and / or time information for sending the second request message.

[0007] Based on the above scheme, if the configuration for data collection by the first communication device transmitted on the network side or the training dataset or model parameters on the network side are lost, the terminal device can flexibly request the network device to resend the data according to the number of times and / or time information of sending the second request message, thereby reducing signaling overhead and transmission load.

[0008] In conjunction with the first aspect, in some implementations of the first aspect, the first information indicates at least one of the following: the time interval between sending two adjacent request messages, the two adjacent request messages including the first request message and the second request message; whether to resend the request message in the event that the first configuration information is lost or the first data is lost; a threshold corresponding to the number of times the request message is resent; wherein the resent request message includes the second request message.

[0009] In conjunction with the first aspect, in some implementations of the first aspect, the threshold includes a first threshold and a second threshold. The first threshold is the threshold corresponding to the number of times the resent request message is sent when the resent request message is used to request the training dataset on the second communication device side. The second threshold is the threshold corresponding to the number of times the resent request message is sent when the resent request message is used to request the model parameters on the second communication device side. The first threshold is less than the second threshold.

[0010] Based on the above scheme, by setting a threshold for the number of times a request to resend the training dataset corresponding to the second communication device to be less than the threshold for the number of times a request to resend the model parameters corresponding to the second communication device to be resent, the first communication device can flexibly request the network device to resend data, thereby reducing signaling overhead and transmission load.

[0011] In conjunction with the first aspect, in some implementations of the first aspect, the first information is carried in a system message; or, the first information is pre-configured.

[0012] In conjunction with the first aspect, in some implementations of the first aspect, the system message originates from the central unit of the second communication device.

[0013] In conjunction with the first aspect, in some implementations of the first aspect, after sending a second request message to the second communication device based on the first information, second configuration information or second data is received from the second communication device. The second configuration information includes relevant configuration information for the first communication device to collect the data, and the second data includes training datasets or model parameters on the side of the second communication device. If it is determined that the second configuration information or the second data is not lost, a first indication message is sent to the second communication device, and the first indication message indicates the end of the request.

[0014] Based on the above scheme, when the first communication device receives complete data after resending the request message, by sending an indication message to the network side to end the request, the network side can release the configuration related to the data collection of the first communication device, thereby reducing memory usage.

[0015] In conjunction with the first aspect, in some implementations of the first aspect, if the first request message requests the training dataset or model parameters of the second communication device, then after sending the second request message to the second communication device according to the first information, second data from the second communication device is received, the second data including the training dataset or model parameters of the second communication device; if it is determined that the second data is lost, the second request message is sent to the second communication device, the second request message being used to request the retransmission of the training dataset or model parameters of the second communication device, or the second request message being used to request the lost data in the second data.

[0016] Based on the above scheme, if the first communication device still does not receive complete data after resending the request message, the first communication device can request the data or lost data again from the network side in order to obtain complete data.

[0017] In conjunction with the first aspect, in some implementations of the first aspect, when the number of times the second request message is sent reaches a threshold, a second indication message is sent to the second communication device, the second indication message indicating the end of the request.

[0018] In conjunction with the first aspect, in some implementations of the first aspect, auxiliary information is sent to the second communication device; if the second request message is used to request the training dataset on the side of the second communication device, the auxiliary information instructs the first communication device to use a portion of the data in the training dataset for model training; if the second request message is used to request the model parameters on the side of the second communication device, the auxiliary information instructs the first communication device to use a portion of the parameters in the model parameters, and the auxiliary information also includes the values ​​of other parameters in the model parameters obtained by the first communication device training, excluding the portion of parameters.

[0019] Based on the above scheme, if the number of times the first communication device sends request messages reaches a threshold and no complete data is received, the first communication device can send auxiliary information to the network side so that the network side can know the data utilization information of the first communication device, which is beneficial for the network side to make subsequent decisions.

[0020] In conjunction with the first aspect, in some implementations of the first aspect, the first data includes N data blocks segmented by the radio resource control layer, where N is a positive integer, and the identification information of the data blocks is used to determine whether the first data is lost.

[0021] Based on the above scheme, the first communication device can determine whether the received data is lost based on the identifier of the segmented data block.

[0022] In conjunction with the first aspect, in some implementations of the first aspect, the first request message is sent to the distributed unit of the second communication device.

[0023] Based on the above scheme, in a scenario where the central unit and distributed unit of the second communication device are separated, the first communication device can re-request data from the network side if the data received from the network side is lost.

[0024] For example, the above AI model can be used for beam management, mobility management, channel state information (CSI) feedback, or location.

[0025] Secondly, a communication method is provided, which can be executed by a second communication device, which can be a network device, or a component of the network device (e.g., a chip or circuit), without limitation.

[0026] The method includes: receiving a first request message from a first communication device, the first request message requesting configuration information related to data collection by the first communication device, or the first request message requesting a training dataset or model parameters from a second communication device, the training dataset including a dataset used by the second communication device to train an artificial intelligence (AI) model, the model parameters including parameters of the AI ​​model after model training; sending first configuration information or first data to the first communication device, the first configuration information including configuration information related to data collection by the first communication device, the first data including the training dataset or model parameters from the second communication device; receiving a second request message from the first communication device, the second request message being used to obtain complete configuration information related to data collection by the first communication device or the training dataset or model parameters from the second communication device, the second request message being sent based on first information, the first information indicating the number of times and / or time information of sending the second request message.

[0027] Based on the above scheme, if the configuration for data collection by the first communication device transmitted on the network side or the training dataset or model parameters on the network side are lost, the network side can receive a request message resent by the first communication device. This request message is sent based on the number of request messages and / or time information, thereby reducing signaling overhead and transmission load.

[0028] For example, the specific content and transmission method of the first information are described in the first aspect.

[0029] In conjunction with the second aspect, in some implementations of the second aspect, after receiving a second request message from the first communication device, second configuration information or second data is sent to the first communication device. The second configuration information includes relevant configuration information for the first communication device to collect the data, and the second data includes training datasets or model parameters on the side of the second communication device. A first indication message is received from the first communication device, which indicates an end request. The first indication message is sent if the second configuration information or the second data is not lost.

[0030] Based on the above scheme, by receiving the first instruction information, the second communication device can release the configuration related to data collection by the first communication device, thereby reducing memory usage.

[0031] In conjunction with the second aspect, in some implementations of the second aspect, if the first request message requests the training dataset or model parameters on the second communication device side, then after receiving the second request message from the first communication device, second data is sent to the first communication device, the second data including the training dataset or model parameters on the second communication device side; the second request message is received from the first communication device, the second request message requesting retransmission of the training dataset or model parameters of the second communication device, or the second request message requesting missing data in the second data.

[0032] In conjunction with the second aspect, in some implementations of the second aspect, a second instruction message is received from the first communication device, the second instruction message indicating an end request; and the configuration related to data collection by the first communication device is released according to the second instruction message.

[0033] In conjunction with the second aspect, in some implementations of the second aspect, auxiliary information is received from the first communication device; if the second request message requests the training dataset on the side of the second communication device, the auxiliary information instructs the first communication device to use a portion of the data in the training dataset for model training; if the second request message requests the model parameters on the side of the second communication device, the auxiliary information instructs the first communication device to use a portion of the parameters in the model parameters, and the auxiliary information also includes the values ​​of other parameters in the model parameters obtained by the first communication device training, excluding the portion of parameters.

[0034] Based on the above scheme, by receiving this auxiliary information, the second communication device can obtain the data utilization information on the side of the first communication device, which is beneficial for the second communication device to make subsequent decisions.

[0035] In conjunction with the second aspect, in some implementations of the second aspect, the first data includes N data blocks segmented at the radio resource control layer, where N is a positive integer.

[0036] In conjunction with the second aspect, in some implementations of the second aspect, the first request message is received through a distributed unit of the second communication device.

[0037] For example, the AI ​​model can refer to the description in the first aspect.

[0038] Thirdly, a communication device is provided, comprising a transceiver unit, the transceiver unit being configured to: send a first request message to a second communication device, the first request message being configured to request relevant configuration information for data collection by the device, or the first request message being configured to request training datasets or model parameters on the side of the second communication device, the training dataset including datasets used by the second communication device to train an artificial intelligence (AI) model, the model parameters including parameters of the AI ​​model after model training; receive first configuration information or first data from the second communication device, the first configuration information including relevant configuration information for data collection by the device, the first data including training datasets or model parameters on the side of the second communication device; and, if it is determined that the first configuration information or the first data is lost, send a second request message to the second communication device according to first information, the second request message being configured to obtain complete relevant configuration information for data collection by the device or training datasets or model parameters on the side of the second communication device, the first information indicating the number of times and / or time information for sending the second request message.

[0039] In conjunction with the third aspect, in some implementations of the third aspect, the first information indicates at least one of the following: the time interval between sending two adjacent request messages, the two adjacent request messages including the first request message and the second request message; whether to resend the request message in the event that the first configuration information is lost or the first data is lost; a threshold corresponding to the number of times the request message is resent; wherein the resent request message includes the second request message.

[0040] In conjunction with the third aspect, in some implementations of the third aspect, the threshold includes a first threshold and a second threshold. The first threshold is the threshold corresponding to the number of times the resent request message is sent when the resent request message is used to request the training dataset on the second communication device side. The second threshold is the threshold corresponding to the number of times the resent request message is sent when the resent request message is used to request the model parameters on the second communication device side. The first threshold is less than the second threshold.

[0041] In conjunction with the third aspect, in some implementations of the third aspect, the first information is carried in a system message; or, the first information is pre-configured.

[0042] In conjunction with the third aspect, in some implementations of the third aspect, the system message originates from the central unit of the second communication device.

[0043] In conjunction with the third aspect, in some implementations of the third aspect, the transceiver unit is further configured to: receive second configuration information or second data from the second communication device, the second configuration information including relevant configuration information for the device to collect the data, and the second data including training datasets or model parameters on the side of the second communication device; and, if it is determined that the second configuration information or the second data is not lost, send a first indication information to the second communication device, the first indication information indicating an end request.

[0044] In conjunction with the third aspect, in some implementations of the third aspect, if the first request message requests the training dataset or model parameters of the second communication device, the transceiver unit is further configured to: receive second data from the second communication device, the second data including the training dataset or model parameters of the second communication device; if it is determined that the second data is lost, the transceiver unit is further configured to: send the second request message to the second communication device, the second request message being used to request the retransmission of the training dataset or model parameters of the second communication device, or the second request message being used to request the lost data in the second data.

[0045] In conjunction with the third aspect, in some implementations of the third aspect, if the number of times the second request message is sent reaches a threshold, the transceiver unit is further configured to: send a second indication message to the second communication device, the second indication message indicating the end of the request.

[0046] In conjunction with the third aspect, in some implementations of the third aspect, the transceiver unit is further configured to: send auxiliary information to the second communication device; if the second request message is used to request a training dataset on the side of the second communication device, the auxiliary information instructs the device to use a portion of the data in the training dataset for model training; if the second request message is used to request model parameters on the side of the second communication device, the auxiliary information instructs the device to use a portion of the parameters in the model parameters, and the auxiliary information also includes the values ​​of other parameters in the model parameters obtained by the device training, excluding the portion of the parameters.

[0047] In conjunction with the third aspect, in some implementations of the third aspect, the device further includes a processing unit, wherein the first data comprises N data blocks segmented at the radio resource control layer, where N is a positive integer, and the processing unit is configured to: determine whether the first data is lost based on the identification information of the data blocks.

[0048] In conjunction with the third aspect, in some implementations of the third aspect, the transceiver unit is further configured to: send the first request message to the distributed unit of the second communication device.

[0049] Fourthly, a communication device is provided, comprising a transceiver unit, the transceiver unit being configured to: receive a first request message from a first communication device, the first request message requesting configuration information related to data collection by the first communication device, or the first request message requesting a training dataset or model parameters from a second communication device, the training dataset including a dataset used by the device to train an artificial intelligence (AI) model, the model parameters including parameters of the AI ​​model after model training; send first configuration information or first data to the first communication device, the first configuration information including configuration information related to data collection by the first communication device, the first data including the training dataset or model parameters from the device; receive a second request message from the first communication device, the second request message being used to obtain complete configuration information related to data collection by the first communication device or the training dataset or model parameters from the device, the second request message being sent based on first information, the first information indicating the number of times and / or time information of sending the second request message.

[0050] For example, the specific content and transmission method of the first information are described in the first aspect.

[0051] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the transceiver unit is further configured to: send second configuration information or second data to the first communication device, the second configuration information including relevant configuration information for the first communication device to collect the data, and the second data including training datasets or model parameters on the device side; receive first indication information from the first communication device, the first indication information indicating an end request, the first indication information being sent if the second configuration information or the second data is not lost.

[0052] In conjunction with the fourth aspect, in some implementations of the fourth aspect, if the first request message requests the training dataset or model parameters on the device side, the transceiver unit is further configured to send second data to the first communication device, the second data including the training dataset or model parameters on the device side; receive the second request message from the first communication device, the second request message requesting retransmission of the training dataset or model parameters of the device, or the second request message requesting lost data in the second data.

[0053] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the transceiver unit is further configured to: receive a second indication message sent from the first communication device, the second indication message indicating an end request; the device further includes a processing unit configured to release configurations related to data collection by the first communication device according to the second indication message.

[0054] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the transceiver unit is further configured to: receive auxiliary information from the first communication device; if the second request message requests the training dataset on the device side, the auxiliary information instructs the first communication device to use a portion of the data in the training dataset for model training; if the second request message requests the model parameters on the device side, the auxiliary information instructs the first communication device to use a portion of the parameters in the model parameters, and the auxiliary information also includes the values ​​of other parameters in the model parameters obtained by the first communication device training, excluding the portion of parameters.

[0055] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the second data includes N data blocks segmented at the radio resource control layer, where N is a positive integer.

[0056] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the transceiver unit receives the first request message through the distributed unit of the device.

[0057] For example, the AI ​​model can refer to the description in the first aspect.

[0058] Fifthly, a communication apparatus is provided for performing the method provided in any one of the first to second aspects. Specifically, the apparatus may include units and / or modules for performing the method provided in any implementation of any of the first to second aspects, such as processing units and / or transceiver units. The communication apparatus may be a terminal device or a network device.

[0059] In one implementation, the device is a communication device. When the device is a communication device, the transceiver unit can be a transceiver or an input / output interface; the processing unit can be at least one processor. Optionally, the transceiver can be a transceiver circuit. Optionally, the input / output interface can be an input / output circuit.

[0060] In another implementation, the device is a chip, chip system, or circuit used in a communication device. When the device is a chip, chip system, or circuit used in a communication device, the transceiver unit can be an input / output interface, interface circuit, output circuit, input circuit, pin, or related circuit on the chip, chip system, or circuit; the processing unit can be at least one processor, processing circuit, or logic circuit.

[0061] A sixth aspect provides a communication device comprising: a memory for storing a program; and at least one processor for executing the computer program or instructions stored in the memory to perform the method provided by any implementation of any of the first to second aspects. The communication device may be a terminal device or a network device.

[0062] In one implementation, the device is a communication device.

[0063] In another implementation, the device is a chip, chip system, or circuit used in a communication device.

[0064] In a seventh aspect, this application provides a processor for performing the methods provided in the foregoing aspects.

[0065] Unless otherwise specified, or if it does not contradict its actual function or internal logic in the relevant description, the transmission and acquisition / reception operations involved in the processor can be understood as processor output and input operations, or as transmission and reception operations performed by radio frequency circuits and antennas. This application does not limit them in this regard.

[0066] Eighthly, a computer-readable storage medium is provided that stores program code for execution by a device, the program code including a method for performing any of the above-described implementations of any of the first to second aspects.

[0067] Ninth aspect, a computer program product containing instructions is provided, which, when run on a computer, causes the computer to perform the method provided by any of the above-described implementations of any of the first to second aspects.

[0068] In a tenth aspect, a chip is provided, the chip including a processor and a communication interface, the processor reading instructions stored in a memory through the communication interface and executing the method provided by any of the above implementations of the first to second aspects.

[0069] Optionally, as one implementation, the chip also includes a memory storing computer programs or instructions. The processor is used to execute the computer programs or instructions stored in the memory. When the computer programs or instructions are executed, the processor is used to execute the method provided by any of the above implementations of the first to second aspects.

[0070] Eleventhly, a communication system is provided, including the aforementioned terminal equipment and / or network equipment. Attached Figure Description

[0071] Figure 1 This is a schematic diagram of the communication system 100 applicable to this application.

[0072] Figure 2 This is a schematic diagram of the communication system 200 applicable to this application.

[0073] Figure 3 This is a schematic diagram of an application framework applicable to this application.

[0074] Figure 4 This is a schematic diagram of the application architecture of the AI ​​model applicable to this application.

[0075] Figure 5 This is a schematic diagram of wide beam and narrow beam applicable to this application.

[0076] Figure 6 This is a flowchart of AI-based CSI feedback.

[0077] Figure 7 A schematic flowchart of a communication method 700 provided in this application.

[0078] Figure 8 This is a schematic diagram of a communication device 1000 provided in an embodiment of this application.

[0079] Figure 9 This is a schematic diagram of another communication device 1100 provided in an embodiment of this application.

[0080] Figure 10 This is a schematic diagram of a chip system 1200 provided in an embodiment of this application. Detailed Implementation

[0081] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0082] The technical solutions provided in this application can be applied to various communication systems, such as: 5th generation (5G) or new radio (NR) systems, long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, wireless local area network (WLAN) systems, satellite communication systems, future communication systems, or integrated systems of multiple systems. The technical solutions provided in this application can also be applied to device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), and Internet of Things (IoT) communication systems or other communication systems.

[0083] The terminal devices in this application include various devices with wireless communication capabilities, which can be used to connect people, objects, machines, etc. These terminal devices can be widely applied in various scenarios, such as: cellular communication, D2D, V2X, peer-to-peer (P2P), M2M, MTC, IoT, virtual reality (VR), augmented reality (AR), industrial control, autonomous driving, telemedicine, smart grids, smart furniture, smart offices, smart wearables, smart transportation, smart cities, drones, robots, remote sensing, passive sensing, positioning, navigation and tracking, autonomous delivery, etc. The terminal device can be a terminal in any of the above scenarios, such as an MTC terminal, an IoT terminal, etc. Terminal equipment can be a user equipment (UE), terminal, fixed equipment, mobile station equipment or mobile device, subscriber unit, handheld device, vehicle-mounted equipment, wearable device, cellular phone, smartphone, session initialization protocol (SIP) phone, wireless data card, personal digital assistant (PDA), computer, tablet computer, laptop computer, wireless modem, handset, laptop computer, computer with wireless transceiver capability, smart book, vehicle, satellite, global positioning system (GPS) device, target tracking device, aircraft (e.g., drone, helicopter, multi-helicopter, quad-helicopter, or airplane), boat, remote control device, smart home device, industrial equipment, or a device built into the above devices (e.g., a communication module, modem, or chip in the above devices), or other processing devices connected to a wireless modem. For ease of description, the terminal equipment will be described below using terminals or UEs as examples.

[0084] It should be understood that in certain scenarios, a UE can also be used as a base station. For example, a UE can act as a scheduling entity, providing sidelink signaling between UEs in scenarios such as V2X, D2D, or P2P.

[0085] In this embodiment, the device for implementing the functions of the terminal device can be the terminal device itself, or it can be a device that supports the terminal device in implementing the functions, such as a chip system or a chip. This device can be installed in the terminal device. In this embodiment, the chip system can be composed of chips, or it can include chips and other discrete devices.

[0086] The network device in this application embodiment can be a device or module with corresponding communication functions. The network device can be a device used to communicate with terminal devices; it can also be called an access network device or a wireless access network device, such as a base station. In this application embodiment, the network device can refer to a radio access network (RAN) node (or device) that connects the terminal device to the wireless network. A base station can broadly encompass, or be replaced by, various names including: NodeB, evolved NodeB (eNB), next-generation NodeB (gNB), relay station, access point, transmitting and receiving point (TRP), transmitter, master station, auxiliary station, multiple standard radio (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), positioning node, etc. A base station can be a macro base station, micro base station, relay node, donor node, or similar, or a combination thereof. A base station can also refer to a communication module, modem, or chip installed within the aforementioned equipment or apparatus. A base station can also be a mobile switching center, a device that performs base station functions in D2D, V2X, and M2M communications, or a device that performs base station functions in future communication systems. A base station can support networks using the same or different access technologies. The embodiments of this application do not limit the specific technologies or device forms used in the network equipment.

[0087] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move depending on the location of the mobile base station. In other examples, a helicopter or drone can be configured as a device to communicate with another base station.

[0088] In some deployments, the network devices mentioned in this application may be devices including CU, or DU, or devices including CU and DU, or devices with control plane CU nodes (central unit-control plane (CU-CP)) and user plane CU nodes (central unit-user plane (CU-UP)) and DU nodes.

[0089] In some deployments, multiple RAN nodes collaborate to assist terminal devices in achieving wireless access, with different RAN nodes each implementing some of the base station's functions. For example, RAN nodes can be CUs, DUs, CU-CPs, CU-UPs, or radio units (RUs). CUs and DUs can be configured separately or included in the same network element, such as a BBU. RUs can be included in radio equipment or radio units, such as RRUs, AAUs, or RRHs.

[0090] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, a radio access network can also be an open radio access network (O-RAN or ORAN) architecture. In an O-RAN system, CU can also be called an open CU (openCU, O-CU), DU can also be called an open DU (open DU, O-DU), CU-CP can also be called an open CU-CP (O-CU-CP), CU-UP can also be called an open CU-UP (O-CU-UP), and RU can also be called an open RU (openRU, O-RU). Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software modules and hardware modules.

[0091] In this embodiment, the apparatus for implementing the function of the network device can be the network device itself, or it can be an apparatus capable of supporting the network device in implementing that function, such as a chip system or a chip. This apparatus can be installed within the network device. In this embodiment, the chip system can be composed of chips, or it can include chips and other discrete components.

[0092] Network devices and terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can also be deployed in the air on airplanes, balloons, and satellites. This application does not limit the scenario in which the network devices and terminal devices are located. Furthermore, terminal devices and network devices can be hardware devices, software functions running on dedicated hardware, or software functions running on general-purpose hardware, such as virtualization functions instantiated on a platform (e.g., a cloud platform), or entities that include dedicated or general-purpose hardware devices and software functions. This application does not limit the specific form of the terminal devices and network devices.

[0093] Figure 1 This is a schematic diagram of a communication system 100 applicable to embodiments of this application. For example... Figure 1 As shown, the communication system includes an access network 100. Access network 100 can be an access network in a future communication system or a traditional (e.g., 5G, 4G, 3G, or 2G) access network. One or more terminal devices (120a-120j, collectively referred to as 120) can be interconnected or connected to one or more network devices (110a, 110b, collectively referred to as 110) in the wireless access network 100. It should be understood that... Figure 1 This is just an illustration; the communication system may also include other equipment, such as core network equipment, wireless relay equipment, and / or wireless backhaul equipment. Figure 1 Not shown in the image.

[0094] In practical applications, this communication system may include multiple network devices (also known as access network devices) and multiple terminal devices simultaneously, without limitation. A network device can serve one or more terminal devices simultaneously. A terminal device can also access one or more network devices simultaneously. This application does not limit the number of terminal devices and network devices included in this wireless communication system.

[0095] The communication system may also include one or more network elements with artificial intelligence (AI) capabilities. These one or more AI-enabled network elements can perform one or more of the following AI model design-related processes: data collection (e.g., collecting training data and / or inference data), model training, and model inference.

[0096] In one possible design, AI functions (such as AI modules or AI entities) can be configured within existing network elements in the communication system to implement AI-related operations, such as AI model training and / or inference. These existing network elements can be access network devices (such as gNBs), terminal devices, core network devices, or network management systems. The network management system can monitor network operating status, optimize network connectivity and performance, improve network stability, and reduce network maintenance costs.

[0097] In another possible design, an independent network element can be introduced into the communication system to perform AI-related operations, such as training AI models. This independent network element can be called an AI network element or an AI node, etc., with no limitation on the name. This AI network element can connect directly to the access network equipment in the communication system, or it can connect to the access network equipment through a third-party network element. The third-party network element can be a core network device such as a user plane function (UPF) network element, a network management system, a cloud server, or other network elements, without limitation. This AI network element can be a hardware device, a software function running on dedicated hardware, or a software function running on general-purpose hardware, such as a virtualization function instantiated on a platform (e.g., a cloud platform), or an entity that includes dedicated or general-purpose hardware devices and software functions. Optionally, it can reside in a server, such as a host in an over-the-top (OTT) system or a cloud server.

[0098] In this application, a model (such as an AI model) can infer one parameter or multiple parameters. The training processes of different models can be deployed on different devices or nodes, or on the same device or node. The inference processes of different models can be deployed on different devices or nodes, or on the same device or node; there is no limitation in this regard.

[0099] This application involves the processing or manipulation of models, such as model training and model inference. Model training may include one or more of the following: initial model training, retraining, model updating, and verification or monitoring of model performance.

[0100] Figure 2 This is a schematic diagram of a communication system 200 applicable to embodiments of this application. The communication system 200 includes core network equipment, access network equipment, and UE, and each network element can be configured with one or more AI models. As an example, the communication system 200 may further include... Figure 2 Other components besides those shown are not limited in this application.

[0101] like Figure 2As shown, access network devices can communicate with core network (CN) devices via an interface (e.g., NG interface or Xn). Access network devices can also communicate with at least one UE via an air interface (Uu interface). One or more AI modules are deployed in one or more of the core network devices, access network devices, and UEs (for example,...). Figure 2 (Only one is shown in the image). The access network device can be a single RAN node or include multiple RAN nodes, such as a CU and a DU. The CU can connect to the DU via interfaces, such as the F1 interface. One or more AI modules can be deployed in the CU and / or DU respectively. Optionally, the CU can also be split into CU-CP and CU-UP. CU-CP and CU-UP can connect to the DU via the control plane F1-C interface and the user plane F1-U interface respectively. One or more AI models are configured in CU-CP and / or CU-UP.

[0102] This AI module is used to implement corresponding AI functions. AI modules deployed in different devices can be the same or different. Depending on the parameter configuration, the AI ​​module can achieve different functions. The AI ​​module model can be configured based on one or more of the following parameters: structural parameters (e.g., at least one of the following: number of neural network layers, neural network width, inter-layer connections, neuron weights, neuron activation function, or biases in the activation function), input parameters (e.g., the type and / or dimension of the input parameters), or output parameters (e.g., the type and / or dimension of the output parameters). The biases in the activation function can also be referred to as the biases of the neural network.

[0103] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or they can be deployed on the same node or device, without restriction.

[0104] Figure 3 This is a schematic diagram illustrating another application framework applicable to the embodiments of this application. For example... Figure 3 As shown, the communication system includes a RAN intelligent controller (RIC). For example, the RIC could be... Figure 2The AI ​​module shown is used to implement AI-related functions. RICs include near-real-time RICs (near-RT RICs) and non-real-time RICs (non-RT RICs). Non-real-time RICs primarily process non-real-time information, such as data that is not sensitive to latency, with latency in the order of seconds. Real-time RICs primarily process near-real-time information, such as data that is relatively sensitive to latency, with latency in the order of tens of milliseconds.

[0105] Near real-time RICs are used for model training and inference. For example, they are used to train AI models and then use those models for inference. Near real-time RICs can obtain network-side and / or terminal-side information from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or inference data.

[0106] Optionally, near real-time RIC can deliver inference results to RAN nodes and / or terminals.

[0107] Optionally, inference results can be exchanged between CU and DU, and / or between DU and RU. For example, near real-time RIC submits inference results to DU, and DU sends them to RU.

[0108] Non-real-time RICs are also used for model training and inference. For example, they are used to train AI models and then use those models for inference. Non-real-time RICs can obtain network-side and / or terminal-side information from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or inference data, and the inference results can be delivered to the RAN nodes and / or terminals.

[0109] Optionally, inference results can be exchanged between CU and DU, and / or between DU and RU. For example, a non-real-time RIC can submit inference results to DU, which in turn can send them to RU.

[0110] Near real-time RICs and non-real-time RICs can also be configured as separate devices. Alternatively, near real-time RICs and non-real-time RICs can also be part of other devices. For example, near real-time RICs can be configured in RAN nodes (e.g., CU, DU), while non-real-time RICs can be configured in OAM, cloud servers, core network devices, or other network devices.

[0111] To facilitate understanding of the embodiments of this application, the terms involved in this application will be briefly explained below.

[0112] 1. Artificial Intelligence (AI): This refers to the use of computers to simulate and extend human consciousness, thought processes, and intelligent behaviors (such as learning, reasoning, thinking, and planning), enabling computers to achieve higher-level applications. Artificial intelligence can be understood as the intelligence exhibited by machines created by humans. Generally, artificial intelligence refers to the technology of presenting human intelligence through computer programs. The goals of artificial intelligence include understanding intelligence by constructing computer programs that demonstrate symbolic reasoning or reasoning.

[0113] 2. Machine Learning (ML): ML is an important technical approach to realizing AI. Deep neural networks (DNNs) are a specific implementation of ML. According to the general approximation theorem, neural networks can theoretically approximate any continuous function, thus enabling them to learn arbitrary mappings. Traditional communication systems require extensive expert knowledge to design communication modules, while DNN-based deep learning communication systems can automatically discover hidden pattern structures from large datasets, establish mapping relationships between data, and achieve performance superior to traditional modeling methods.

[0114] Based on their construction methods, DNNs can be categorized into feedforward neural networks (FNNs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs). Among these, CNNs are specifically designed to process data with a grid-like structure. For example, time-series data (discrete sampling along the time axis) and image data (two-dimensional discrete sampling) can both be considered as grid-like data. CNNs do not utilize all the input information at once; instead, they use a fixed-size window to extract a portion of the information for convolution operations, significantly reducing the computational cost of model parameters. Furthermore, depending on the type of information extracted by the window (e.g., people and objects in an image represent different types of information), each window can use different convolution kernels, allowing CNNs to better extract features from the input data.

[0115] Recurrent Neural Networks (RNNs) are a type of distributed neural network (DNN) that utilizes feedback time-series information. Their input includes the current input value and their output value from the previous time step. RNNs are well-suited for acquiring temporally correlated sequence features and are applicable to applications such as speech recognition and channel coding / decoding.

[0116] The FNN, CNN, and RNN mentioned above are common neural network structures, all of which are constructed based on neurons.

[0117] 3. AI Model: This can refer to an algorithm or computer program that can implement AI functions. An AI model represents the mapping relationship between the model's input and output; in other words, an AI model is a function model that maps an input of a certain dimension to an output of a certain dimension. The parameters of the function model can be obtained through machine learning training. For example, f(x) = ax 2 +b is a quadratic function model, which can be viewed as an AI model. a and b are the parameters (or model parameters) of this AI model, and a and b can be obtained through machine learning training.

[0118] The AI ​​models mentioned in this application include, but are not limited to, neural networks, linear regression models, decision tree models, support vector machines (SVM), Bayesian networks, Q-learning models, or other ML models.

[0119] It should be understood that AI models can be implemented in hardware circuits, software, or a combination of both; there are no restrictions. Non-restrictive examples of software include: program code, program, subroutine, instructions, instruction sets, code, code segments, software modules, application programs, or software applications, etc.

[0120] 4. AI Model Training and AI Model Inference:

[0121] AI models need to be trained before they can be used to solve specific technical problems.

[0122] Figure 4 This is a schematic diagram of an AI / ML model application framework. For example... Figure 4 As shown in (a), AI model training (or simply model training) refers to the process of using a specified initial model to compute on training data (or training dataset), and then adjusting the model parameters in the initial model using certain methods based on the computation results, so that the model gradually learns certain rules and acquires specific functions. After training, an AI model with stable functions can be used for inference. AI model inference is the process of using the trained AI model to compute on the input data and obtain predicted inference results.

[0123] In this application, model parameters may include parameters such as the number of layers in the neural network, the number of neurons, the activation function, and the loss function.

[0124] Taking AI models as deep learning models as an example, in the training phase, it is first necessary to construct a training set for the deep learning model based on the objective. The training set includes multiple training data, each of which is labeled. The label of the training data is the correct answer of that training data on a specific question. The label can represent the objective of using the training data to train the deep learning model.

[0125] When training a deep learning model, training data can be input into the model in batches after parameter initialization. The deep learning model performs calculations (i.e., "inference") on the training data to obtain prediction results. The prediction results obtained through inference, along with the corresponding labels of the training data, are used as data for calculating the loss function. The loss function is used during the model training phase to calculate the difference (i.e., the "loss value") between the model's prediction result for the training data and the label of that training data. The loss function can be implemented using different mathematical functions; commonly used loss function expressions include: mean squared error loss function, logarithmic loss function, least squares method, etc. Model training is a repetitive iterative process. Each iteration performs inference on different training data and calculates the loss value. The goal of multiple iterations is to continuously update the parameters of the deep learning model and find the parameter configuration that minimizes or stabilizes the loss value of the loss function.

[0126] like Figure 4 As shown in (b), when this framework is applied to an NR system, it can include several functional modules (or entities) such as data collection, model training, model inference, and actor. The data collection entity serves as a database for AI model training and data analysis inference, storing data inputs from gNB, gNB-CU, gNB-DU, UE, or other management entities. The model training entity analyzes the training data provided by the data collection entity to provide the optimal AI model. The model inference entity uses the AI ​​model, based on the data provided by the data collection entity, to provide reasonable predictions about network operation or guide network policy adjustments. These policy adjustments can be uniformly planned by the actor and sent to multiple network entities for execution. Simultaneously, the network's specific performance after applying relevant policies can be re-entered into the database for storage. Applying AI / ML to NR, through intelligent data collection and analysis, can improve network performance and user experience. For example, it can achieve functions such as energy saving, load balancing, and mobility parameter optimization.

[0127] 5. Training dataset and inference data:

[0128] Training datasets are used to train AI models. A training dataset can include the AI ​​model's input, or it can include both the AI ​​model's input and the target output. Specifically, a training dataset includes one or more training data points, which can be training samples input to the AI ​​model or the AI ​​model's target output. The target output can also be referred to as the label or labeled samples. The training dataset is a crucial part of machine learning; model training essentially involves learning certain characteristics from the training data to make the AI ​​model's output as close as possible to the target output—for example, minimizing the difference between the AI ​​model's output and the target output. The composition and selection of the training dataset can, to a certain extent, determine the performance of the trained AI model. Model performance can be measured, for example, by metrics such as "loss value" and "inference accuracy."

[0129] Furthermore, a loss function can be defined during the training process of an AI model (such as a neural network). The loss function describes the difference or discrepancy between the AI ​​model's output value and the target output value. This application does not limit the specific form of the loss function. The training process of an AI model involves adjusting the model parameters to make the loss function value less than a threshold value, or to make the loss function value meet the target requirements. For example, if the AI ​​model is a neural network, adjusting the model parameters of the neural network includes adjusting at least one of the following parameters: the number of layers in the neural network, its width, the weights of neurons, or the parameters in the activation function of neurons.

[0130] Inference data can be used as input to a trained AI model for inference. During the model's inference process, inputting inference data into the AI ​​model yields the corresponding output, i.e., the inference result.

[0131] 6. Beam: A communication resource. In the NR protocol, the beam can be represented as a spatial filter, or spatial parameters. The beam used to transmit signals can be called the transmission beam (Tx beam), or a spatial domain transmit filter or spatial domain transmit parameter; the beam used to receive signals can be called the reception beam (Rx beam), or a spatial domain receiver filter or spatial domain receive parameter.

[0132] The transmit beam can refer to the distribution of signal strength in different directions in space after a signal is transmitted through an antenna, while the receive beam can refer to the distribution of signal strength in different directions in space of a wireless signal received from an antenna.

[0133] It should be understood that the beamforming examples in the NR protocols listed above are merely illustrative and should not be construed as limiting this application. This application does not preclude the possibility of defining other terms in future protocols to represent the same or similar meanings.

[0134] Furthermore, the beam can be a wide beam, a narrow beam, or other types of beam. The technology used to form the beam can be beamforming technology or other technologies. Beamforming technology can be specifically considered as different resources. The same information or different information can be transmitted through different beams.

[0135] As an example, when using low-frequency or mid-frequency bands, signals can be transmitted omnidirectionally or through a wider angle. When using high-frequency bands, thanks to the smaller carrier wavelength of high-frequency communication systems, antenna arrays consisting of many antenna elements can be arranged at both the transmitting and receiving ends. The transmitting end transmits signals with a certain beamforming weight, making the transmitted signal form a spatially directional beam. At the same time, the receiving end uses an antenna array with a certain beamforming weight to receive the signal, which can improve the received power at the receiving end and counteract path loss.

[0136] Figure 5 This is a schematic diagram of wide beam and narrow beam applicable to embodiments of this application. For example... Figure 5 As shown in (a), network devices and terminal devices can communicate via wide beam or narrow beam. Figure 5 As shown in (b), narrow beams have a spotlight effect, concentrating limited transmission energy in a narrower direction, which can significantly improve the coverage of network devices.

[0137] 7. Beam Scanning: Beam scanning refers to transmitting beams in a predefined direction at fixed intervals within a specific period or time period to cover a specific spatial area. For example, during initial access, the UE needs to synchronize with the system and receive minimum system information. Therefore, a synchronization signal and a physical broadcast channel (PBCH) block (SSB) are scanned and transmitted at fixed intervals. Channel state information reference signal (CSI-RS) can also use beam scanning technology, but covering all predefined beam directions would be too costly. Therefore, CSI-RS is only transmitted in a specific subset of predefined beam directions based on the location of the served terminal equipment.

[0138] 8. Beam Measurement: This refers to the process by which network devices or terminal devices measure the quality and characteristics of the received beamformed signal. During beam management, terminal devices or network devices can obtain information such as reference signal receiving power (RSRP), reference signal receiving quality (RSRQ), and signal-to-interference plus noise ratio (SINR) through SSB and CSI-RS, thereby identifying the best beam.

[0139] 9. Beam Management: Establishing and maintaining a suitable beam pair between network devices and terminal devices. For downlink transmission, the network side needs to select a suitable transmit beam, and the terminal side needs to select a suitable receive beam, which together form a beam pair to maintain a good wireless connection. The beam selection process described above can also be called serving beam selection. Beam management also includes a beam recovery process, which will not be elaborated here.

[0140] 10. AI-based beam management

[0141] The AI ​​can take the received power of a wide beam or a sparsely scanned narrow beam measured on the UE side as input, and the model infers and outputs the Top-k candidate narrow beams (the RSRP value or ID of the output beam set). The network side then performs a scan based on the Top-k candidate beams to finally determine the best beam. Typically, the AI ​​model can be deployed on the UE side or the network side. This application mainly focuses on the application of the UE-side model in the service beam selection scenario.

[0142] 11. AI-based mobility management

[0143] During mobility management, the base station can configure the UE to report measurements and perform handover decisions based on the reported results. With the introduction of AI, the base station can make predictions based on the UE's limited measurement results (e.g., configuring a small number of measurement beams, or reducing the number of times the UE performs beam and cell measurements) and select appropriate cells for handover decisions.

[0144] 12. AI-based positioning

[0145] Existing AI-based positioning scenarios can include the following two types and five scenarios:

[0146] Type 1: Direct AI / ML localization

[0147] Scenario 1 (First Priority): Apply the UE-side model and perform positioning directly based on AI / ML. For example, the UE performs signal measurements, and the positioning result is directly predicted based on the measurement results.

[0148] Case 2 (Second Priority): UE-assisted location management function (LMF) side (LMF receives and processes location requests or location-related data requests, selects a location method based on the request and measures the location result) for positioning. The LMF side uses AI / ML models to perform positioning based on the UE side's assisted information.

[0149] Case 3 (First Priority): RAN-assisted LMF-side localization, where the LMF side uses AI / ML models for localization based on RAN-side assisted information.

[0150] Type 2, AI / ML Assisted Localization

[0151] Case 4 (Second Priority): UE-side model-assisted LMF positioning. The UE side makes predictions based on UE measurement results and sends the prediction results to the LMF to assist the LMF in positioning.

[0152] Case 5 (First Priority): RAN-side model assists LMF localization. The RAN side makes predictions based on the measurement results and sends the prediction results to the LMF to assist the LMF in localization.

[0153] 13. AI-based CSI feedback enhancement

[0154] Existing NR systems use codebooks as the basic tool for CSI feedback, and multiple schemes, such as Type I / II codebooks, have been defined to meet different feedback accuracy requirements. However, these codebooks are all designed for uniformly arranged antenna arrays and are not optimized for special antennas such as 3D antennas, resulting in significant performance limitations. AI-based CSI feedback can overcome these bottlenecks by optimizing for specific channel environments to achieve better feedback performance. The basic principle of AI-based CSI feedback is to treat the high-dimensional channel information feedback task as an end-to-end CSI image compression and reconstruction task.

[0155] Figure 6 The diagram shows a flowchart of AI-based CSI feedback. Figure 6 As shown, its basic signal flow has a structure similar to an autoencoder: 1) The encoder (usually the terminal side) uses an encoder to compress the complete channel information into a bitstream that meets the feedback requirements after feature extraction; 2) This information is fed back to the decoder (usually the base station side) via a feedback link; 3) The decoder uses a decoder to decompress the bitstream information and reconstruct its features, ultimately recovering the complete channel information. The encoder and decoder are jointly optimized during end-to-end training to achieve the best CSI reconstruction performance. In actual deployment, the encoder and decoder need to be paired according to the training process; that is, the compressed CSI output by a certain encoder needs to be recovered using the corresponding decoder.

[0156] Regarding AI-related topics in the air interface (e.g., AI-based beam management, AI-based mobility management, AI-based positioning, or AI-based CSI feedback enhancement), the standard discusses several model deployment methods, such as UE-sided, NW-sided, and two-sided, which means that the model is located on the UE side, the network side (e.g., gNB), and both sides (requiring collaboration between the models on both sides to fulfill the requirements).

[0157] For UE-sided models, it is possible to support the UE requesting the gNB to initiate data collection for the UE-side AI model. The content requested by the UE can be some network-side configurations. The UE can use these configurations to obtain UE-side measurement results, which can then be used as input for training the UE-side model.

[0158] For two-sided models, the UE can request a dataset for training the network-side model. The UE-side model can directly use the same training dataset as the network-side model for training. Alternatively, the UE can request pre-trained model parameters from the network side, meaning the UE obtains the network-side model parameters as its own model parameters and uses these parameters for inference.

[0159] Existing methods for UEs to request data from the network (such as configurations, training datasets, or model parameters used by the UE to obtain measurement results) lack flexibility and may increase signaling overhead or lead to excessive data transmission load. For example, when a UE sends a request message (requesting the network to send configurations used by the UE to obtain measurement results, training datasets used for network-side model training, or model parameters already trained by the network), if packet loss occurs in the request message content, or if the network does not provide timely feedback / response, the UE may frequently resend the request message, and the network may resend a large amount of existing content in response to the repeated request messages, resulting in signaling overhead and transmission load.

[0160] In view of this, this application proposes a communication method in which, when the data (such as training dataset or model parameters) sent by the network device is missing, the terminal device can flexibly request the network device to send the data again, thereby reducing signaling overhead and transmission load.

[0161] It should be noted that in this application, "instruction" can include direct instruction, indirect instruction, explicit instruction, or implicit instruction. When describing instruction information as being used to instruct A, it can be understood that the instruction information carries A, and it can be a direct instruction to A or an indirect instruction to A. Indirect instruction can refer to directly instructing B through the instruction information, and the correspondence between B and A, to achieve the purpose of instructing A through the instruction information. The correspondence between B and A can be predefined by the protocol, pre-stored, or obtained through configuration between communication devices.

[0162] In this application, the information indicated by the instruction information is called the information to be instructed. In specific implementations, there are many ways to indicate the information to be instructed, such as, but not limited to, directly indicating the information to be instructed, such as the information to be instructed itself or its index. It can also indirectly indicate the information to be instructed by indicating other information, where there is a relationship between the other information and the information to be instructed. It can also indicate only a part of the information to be instructed, while the other parts are known or pre-agreed upon. For example, the instruction of specific information can be achieved by using a pre-agreed (e.g., protocol-defined) arrangement of various pieces of information, thereby reducing instruction overhead to some extent. Furthermore, the information to be instructed can be sent as a whole or divided into multiple sub-information pieces, and the sending period and / or timing of these sub-information pieces can be the same or different.

[0163] The term "at least one" in this application refers to one or more items. "More than one" means two or more items. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship. Furthermore, it should be understood that although the terms "first," "second," etc., may be used to describe objects in this application, these objects should not be limited to these terms. These terms are only used to distinguish the objects from each other.

[0164] The methods provided by the embodiments of this application are described in detail below with reference to the accompanying drawings. The embodiments provided by this application can be applied to the above-described embodiments. Figure 1 or Figure 2 The communication system shown is not limited.

[0165] Figure 7 The diagram shown is a schematic representation of a communication method 700 provided in this application. The method includes the following steps.

[0166] S710, the first communication device sends a first request message to the second communication device. Accordingly, the second communication device receives the first request message.

[0167] The first communication device can be a terminal device or a component of a terminal device (such as a chip or circuit), without limitation. The following description uses the first communication device as a terminal device. The second communication device can be a network device or a component of a network device (such as a chip or circuit). The second communication device can also be an independent network element on the network side to perform AI-related operations, without limitation. The following description uses the second communication device as a network device.

[0168] The first request message can be used to request configuration information for data collection by the terminal device. That is, the terminal device can collect data according to this configuration information, and the collected data can be used for model training. In other words, the data collected by the terminal device can serve as a training dataset for model training on the terminal device side. For example, the configuration information could be beam management configuration information sent by a network device, CSI prediction / CSI compression configuration information, or location prediction (or positioning) configuration information.

[0169] Alternatively, the first request message may be used to request the network device to send training data(set) or model parameters. Here, the training data(set) is the dataset used by the network side to train the AI ​​model; the model parameters are the parameters of the AI ​​model deployed on the network side, or in other words, the parameters of the AI ​​model deployed on the network side after training on the training dataset. For example, the training data(set) or model parameters could be the training data(set) or model parameters of an AI model used for CSI feedback enhancement.

[0170] As an example, in a scenario where the CU and DU of a network device are separate, sending a first request message from a terminal device to the network device can mean that the terminal device sends the first request message to the DU of the network device. Similarly, in subsequent scenarios involving a terminal device sending a request message with a similar function to the first request message to the network device, it can mean that the terminal device sends the request message to the DU of that network device.

[0171] S720, the second communication device sends a first configuration or first data to the first communication device. Accordingly, the first communication device receives the first configuration or first data.

[0172] The first configuration refers to configuration information related to data collection by the terminal device; the first data may include training datasets or model parameters used by the network side for AI model training. For example, the first configuration or the first data may be sent by the network device based on the first request message.

[0173] Optionally, if the first data includes a training dataset or model parameters from the network side, the network device segments the training dataset before sending it, that is, it divides the training dataset into N data blocks and sends them, where N is a positive integer. For example, the network device segments the training dataset or model parameters at the application layer or the radio resource control (RRC) layer.

[0174] It should be understood that there are no restrictions on the specific way network devices segment the training dataset or model parameters. For example, network devices can segment the training dataset at the application layer or segment the model parameters at the RRC layer.

[0175] S730, if it is determined that the first configuration information or the first data is lost, the first communication device sends a second request message to the second communication device based on the first information. Correspondingly, the second communication device receives the second request message.

[0176] In this application, the loss of data or information can include the complete loss or partial loss of the data or information. Complete loss of data or information can also be understood as not receiving the data or information. Taking the loss of the first data as an example, the terminal device's determination of the loss of the first data can include the terminal device determining that it did not receive the first data, or the terminal device determining that the received first data suffered packet loss. Furthermore, this application is not limited to the cause of the data or information loss; for example, the loss of data or information may be due to network conditions, or the loss of data or information may also be due to the network device failing to send (or failing to send) the data or information.

[0177] The second request message can be used to obtain complete configuration information for data collection by the terminal device or training datasets or model parameters of the network device. The first information indicates the number of times and / or the timing of sending the second request message. That is, the terminal device determines the sending method of the second request message based on the first information.

[0178] For example, the first information includes at least one of the following: the time interval between sending two adjacent request messages; whether to resend the request message in the event that the first configuration information or the first data is lost; and a threshold corresponding to the number of times the request message is resent.

[0179] It can be understood that the two adjacent request messages include the first request message and the second request message, that is, the first information indicates the time information for sending the second request message; the resent request message includes the second request message, that is, the first information indicates whether to send the second request message if it is determined that the first configuration information or the first data is lost.

[0180] Optionally, the threshold for the number of times the request message is resent may differ depending on the content of the request message.

[0181] For example, the threshold includes a first threshold and a second threshold. The first threshold is the threshold corresponding to the number of times the request message is resent when the resent request message is used to request the training dataset on the network device side, and the second threshold is the threshold corresponding to the number of times the request message is resent when the resent request message is used to request the model parameters on the network device side.

[0182] It should be understood that the values ​​and relationship between the first and second thresholds are not limited and can be set according to the actual situation. For example, the first and second thresholds can be equal in value and be K, where K is an integer greater than or equal to 0. That is, if the first data is received and some of the first data is lost, the terminal device can send a maximum of K requests to obtain the complete data (training dataset or model parameters).

[0183] Furthermore, the first threshold can be set to be less than the second threshold. That is, when a resent request message is used to request training data from the network side, the terminal device can resend the request message more times than when a resent request message is used to request model parameters from the network side. It is understood that the amount of data in the training dataset is usually large, while the amount of data in the model parameters is usually small. Setting the first threshold to be less than the second threshold can reduce the transmission load.

[0184] Optionally, the threshold also includes a third threshold, which is a threshold corresponding to the number of times the request message is resent when the resent request message is used to request configuration information for data collection by the terminal device. The value of the third threshold is not limited and can be set according to actual circumstances. For example, the third threshold can be less than or equal to the first threshold.

[0185] The first information can be pre-configured, i.e., pre-configured in the terminal device, or it can come from the network device. For example, the network device can send the first information to the terminal device via a system message. Exemplarily, in a scenario where the CU and DU of the network device are separate, the system message can come from the CU of the network device. An example of the first information is shown in Table 1.

[0186] Table 1

[0187]

[0188] In Table 1, a value of 0 or 1 for "Allow resending request messages" indicates whether resending request messages is allowed or not. For example, the terminal device sends the second request message when resending is allowed. K1, K2, and K3 can be integers greater than or equal to 0, representing examples of the third threshold, first threshold, and second threshold, respectively. T1, T2, and T3 represent the time interval between sending two consecutive request messages, corresponding to different request message contents. That is, in this application, the time interval between sending two consecutive request messages can also be different when the content of the request messages is different. Furthermore, this application does not limit the specific values ​​and relationships of T1, T2, and T3, and they can be set according to actual circumstances.

[0189] When the second request message is used to obtain complete configuration information for data collection by the terminal device, or training dataset or model parameters of the network device, the second request message may include two implementation methods.

[0190] In one possible implementation, the second request message is used to request the network device to resend configuration information (i.e., configuration information for data collection by the terminal device) or training dataset or model parameters. Alternatively, the second request message is similar to the first request message, but is sent after the first request message to request the network device to send configuration information for data collection by the terminal device, or training data (set) or model parameters from the network device side.

[0191] For example, if it is determined that the first configuration information is lost, or if the first data is segmented at the application layer, the terminal device requests the network device to resend the configuration information (i.e., the configuration information used by the terminal device to collect data) or the training dataset or model parameters.

[0192] In another possible implementation, the second request message is used to request lost data.

[0193] For example, this implementation is applicable to the case where the second request message requests the training dataset or model parameters of the network device; more specifically, this implementation is applicable to the case where the terminal device learns of the specific lost data.

[0194] For example, the first data includes the training dataset or model parameters of the network device segmenting in RRC. The terminal device can determine the missing data in the first data based on the identification information of the segmented data blocks. The second request message can include the identification information (such as the number) of the missing data block.

[0195] For example, the terminal device sending the second request message based on the first information includes: the terminal device sending the second request message to the network device after a first time period following the sending of the first request message. The first time period is the time interval between sending two adjacent request messages. By setting the terminal device to send the second request message after the first time period, frequent requests from the terminal device to the network device can be prevented, thereby reducing signaling overhead and avoiding data overload on the terminal device side.

[0196] Optionally, prior to S730, the method further includes: the terminal device determining that the first configuration information is lost or the first data is lost.

[0197] As an example, the terminal device can determine whether the first data is missing based on the known total amount of data and the amount of the first data received. For instance, if the first data is a training dataset used by the network side, and the amount of the received training dataset is 0, less than the total amount of the training dataset, or the difference between the amount of the training dataset and the total amount of the training dataset is greater than or equal to a threshold, the terminal device can determine that the first data is missing. Similarly, if the first data is model parameters from the network side, the terminal device can also determine whether the first data is missing using the above method. It should be understood that when the network side segments the training dataset at the application layer, the amount of the training dataset can refer to the amount of the training dataset counted by the terminal device at the application layer.

[0198] As another example, the terminal device determines whether the first data is lost based on the identification information (such as number) of the data blocks included in the first data. For example, if the first data is model parameters used by the network side, the network device segments the model parameters at the RRC layer, so the terminal device can count whether the data blocks at the RRC layer are continuous to determine whether the first data sent by the network device is lost.

[0199] As another example, when the first communication device receives the first configuration information, the terminal device can determine whether the first configuration information is missing based on whether it is included.

[0200] It should be understood that the methods described above for determining whether the first data is lost by the terminal device are merely examples and do not constitute a limitation on this application. For example, if the network device segments the training dataset at the RRC layer or segments the model parameters at the application layer, the terminal device can determine whether the training dataset or model parameters are lost according to the corresponding methods.

[0201] Optionally, the method further includes:

[0202] S740, the second communication device sends second configuration information or second data to the first communication device. Accordingly, the first communication device receives the second data.

[0203] The second configuration information refers to the configuration information used by the terminal device for data collection; the second data may include training datasets or model parameters used by the network side for AI model training. The second configuration information or the second data may be information or data sent by the network device based on the second request message.

[0204] As an example, the second configuration information or the second data includes complete information or data, meaning that the second configuration information or the second data is not lost. Alternatively, for data, if the amount of lost data is less than a threshold, it can be considered that the data is not lost. The specific method by which the terminal device determines whether the second configuration information or the second data is lost can be found in the description in S730, and will not be repeated here.

[0205] In this example, the method may further include: the terminal device sending a first indication message to the network device. This first indication message indicates the end of the request, or in other words, it indicates the end of the current data request, or that complete data has been received.

[0206] For example, the first indication information is 1 bit. When the value of this 1 bit is "0" or "1", it indicates the end of the request or that complete data has been received.

[0207] Optionally, after receiving the first instruction information, the network device can clear the configuration related to data collection based on the first instruction information, thereby reducing memory usage.

[0208] It should be understood that this application does not limit the way the first instruction information is sent. For example, the first instruction information may be carried in a request message (such as a first request message and a second request message) sent by the terminal device to request training datasets or model parameters, or the first instruction information may be an instruction information sent separately.

[0209] As another example, the second configuration information or second data may still be missing, meaning that the configuration information sent by the network side for the terminal device to collect data, or the training dataset or model parameters sent by the network side, may still be missing. In this case, the terminal device can repeatedly execute S730, that is, resend the second request message to the network device until the terminal device receives complete data, or the number of requests by the terminal device reaches the threshold corresponding to the number of times the request message is resent as indicated by the first information.

[0210] Optionally, if after K requests (an example of a threshold corresponding to the number of times the request message is resent), the terminal device still receives information or data from the network side that is lost, the terminal device sends a second indication message to the network device, which indicates that the request should be terminated.

[0211] For example, the second indication information is 1 bit, and when the value of this 1 bit is "0" or "1", it indicates the end of the request.

[0212] The terminal device can train the model based on the missing training dataset, or use the missing model parameters.

[0213] Furthermore, the terminal device can also send auxiliary information to the network device, indicating the terminal device's utilization of the network-side training dataset or model parameters. The content of this auxiliary information can vary depending on the content of the request message. For example, if the request message requests training datasets from the network device, the auxiliary information may indicate that a portion of the network-side training dataset was used for training. If the request message requests model parameters from the network device, the auxiliary information may indicate that a portion of the network-side model data was used. Optionally, the terminal device can train the missing model parameters itself and send these missing model parameters to the network device in the auxiliary information.

[0214] Based on the above scheme, the network side responds to the request messages sent by the terminal device for training datasets or model parameters. In the event of packet loss during the transmission of training datasets or model parameters, the terminal device can flexibly request the network device to resend the data, thereby reducing signaling overhead and transmission load.

[0215] It is understood that some optional features in the various embodiments of this application may not depend on other features in some scenarios, or may be combined with other features in some scenarios, without limitation.

[0216] It is also understood that the solutions in the various embodiments of this application can be used in reasonable combinations, and the explanations or descriptions of the various terms appearing in the embodiments can be referenced or explained to each other in the various embodiments, without limitation.

[0217] It can also be understood that the methods and operations implemented by the network element in the above-described method embodiments can also be implemented by components of the network element (such as chips or circuits), without limitation.

[0218] The above, combined with Figures 1 to 7 The methods provided in the embodiments of this application are described in detail below. Figures 8 to 10 The apparatus provided in the embodiments of this application is described in detail. It should be understood that the description of the apparatus embodiments corresponds to the description of the method embodiments. Therefore, for content not described in detail, please refer to the method embodiments above. For the sake of brevity, it will not be repeated here.

[0219] Figure 8 This is a schematic diagram of a communication device 1000 provided in an embodiment of this application. The device 1000 includes a transceiver unit 1010 and a processing unit 1020. The transceiver unit 1010 can be used to implement corresponding communication functions. The transceiver unit 1010 can also be referred to as a communication interface or a communication unit. The processing unit 1020 can be used to perform processing.

[0220] Optionally, the device 1000 may further include a storage unit, which can be used to store instructions and / or data, and the processing unit 1020 can read the instructions and / or data in the storage unit to enable the device to implement the aforementioned method embodiments.

[0221] As a design, the device 1000 is used to execute the steps or processes executed by the first communication device in the above method embodiment, the transceiver unit 1010 is used to execute the transceiver-related operations on the first communication device side in the above method embodiment, and the processing unit 1020 is used to execute the processing-related operations on the first communication device side in the above method embodiment.

[0222] As an alternative design, the device 1000 is used to execute the steps or processes executed by the second communication device in the above method embodiment, the transceiver unit 1010 is used to execute the transceiver-related operations on the second communication device side in the above method embodiment, and the processing unit 1020 is used to execute the processing-related operations on the second communication device side in the above method embodiment.

[0223] It should be understood that the specific process of each unit performing the above-mentioned corresponding steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0224] It should also be understood that the device 1000 here is embodied in the form of a functional unit. The term "unit" here can refer to an application-specific integrated circuit (ASIC), electronic circuitry, a processor (e.g., a shared processor, a proprietary processor, or a group processor, etc.) and memory for executing one or more software or firmware programs, integrated logic circuitry, and / or other suitable components supporting the described functions. In an alternative example, those skilled in the art will understand that the device 1000 can be specifically a device (such as a terminal device or a network device) in the above embodiments, and can be used to execute the various processes and / or steps corresponding to the device in the above method embodiments; to avoid repetition, these will not be described again here.

[0225] The apparatus 1000 of each of the above-described schemes has the function of implementing the corresponding steps performed by the devices (such as terminal devices, network devices, etc.) in the above-described methods. The functions can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions; for example, the transceiver unit can be replaced by a transceiver (e.g., the sending unit in the transceiver unit can be replaced by a transmitter, and the receiving unit in the transceiver unit can be replaced by a receiver), and other units, such as processing units, can be replaced by processors, each executing the transceiver operations and related processing operations in each method embodiment.

[0226] In addition, the transceiver unit 1010 may also be a transceiver circuit (for example, it may include a receiving circuit and a transmitting circuit), and the processing unit may be a processing circuit.

[0227] It should be pointed out that, Figure 10 The device mentioned can be the equipment described in the foregoing embodiments, or it can be a chip or a chip system, such as a system on a chip (SoC). The transceiver unit can be an input / output circuit or a communication interface; the processing unit is a processor, microprocessor, or integrated circuit integrated on the chip. No limitations are imposed here.

[0228] Figure 9 This is a schematic diagram of another communication device 1100 provided in an embodiment of this application. The device 1100 includes a processor 1110, which is coupled to a memory 1120. The memory 1120 is used to store computer programs or instructions and / or data. The processor 1110 is used to execute the computer programs or instructions stored in the memory 1120, or to read the data stored in the memory 1120, in order to execute the methods in the above method embodiments.

[0229] Optionally, there may be one or more processors 1110.

[0230] Optionally, the memory 1120 may be one or more.

[0231] Alternatively, the memory 1120 can be integrated with the processor 1110, or it can be set separately.

[0232] Optionally, such as Figure 9 As shown, the device 1100 also includes a transceiver 1130, which is used for receiving and / or transmitting signals. For example, the processor 1110 is used to control the transceiver 1130 to receive and / or transmit signals.

[0233] As an example, processor 1110 may have Figure 8 The processing unit 1020 shown has the function of a storage unit, the memory 1120 can have the function of a storage unit, and the transceiver 1130 can have the function of a storage unit. Figure 8 The function of the transceiver unit 1010 shown is illustrated.

[0234] As one approach, the device 1100 is used to implement the operations performed by the device (such as a terminal device, or a network device, etc.) in the various method embodiments described above.

[0235] For example, processor 1110 is used to execute computer programs or instructions stored in memory 1120 to implement the relevant operations of the devices (such as terminal devices, network devices, etc.) in the various method embodiments described above.

[0236] It should be understood that the processor mentioned in the embodiments of this application can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0237] It should also be understood that the memory mentioned in the embodiments of this application can be volatile memory and / or non-volatile memory. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM). For example, RAM can be used as an external cache. By way of example and not limitation, RAM includes the following forms: static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0238] It should be noted that when the processor is a general-purpose processor, DSP, ASIC, FPGA, or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, the memory (storage module) can be integrated into the processor.

[0239] Figure 9The device mentioned can be the equipment described in the foregoing embodiments, or it can be a chip or a chip system, such as a system on a chip (SoC). The transceiver can be an input / output circuit or a communication interface; the processor can be a processor, microprocessor, or integrated circuit integrated on the chip. No limitations are imposed here.

[0240] It should also be noted that the memory described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0241] Figure 10 This is a schematic diagram of a chip system 1200 provided in an embodiment of this application. The chip system 1200 (or may also be referred to as a processing system) includes logic circuitry 1210 and an input / output interface 1220.

[0242] The logic circuit 1210 can be a processing circuit in the chip system 1200. The logic circuit 1210 can be coupled to a memory unit, calling instructions from the memory unit, enabling the chip system 1200 to implement the methods and functions of the embodiments of this application. The input / output interface 1220 can be an input / output circuit in the chip system 1200, outputting processed information from the chip system 1200, or inputting data or signaling information to be processed into the chip system 1200 for processing.

[0243] As one approach, the chip system 1200 is used to implement the operations performed by devices (such as terminal devices, or network devices, etc.) in the various method embodiments described above.

[0244] For example, logic circuit 1210 is used to implement processing-related operations performed by a device (such as a terminal device or a network device) in the above method embodiments; input / output interface 1220 is used to implement sending and / or receiving-related operations performed by a device (such as a terminal device or a network device) in the above method embodiments.

[0245] This application also provides a computer-readable storage medium storing computer instructions for implementing the methods executed by a device (such as a terminal device or a network device) in the above-described method embodiments.

[0246] For example, when the computer program is executed by a computer, it enables the computer to implement the methods described in the embodiments of the above methods, which are executed by a device (such as a terminal device or a network device).

[0247] This application also provides a computer program product comprising instructions which, when executed by a computer, implement the methods described above as being executed by a device (such as a terminal device or a network device).

[0248] This application also provides a communication system, which includes the terminal devices and / or network devices described in the above embodiments. For example, the system includes... Figure 7 The terminal device and / or network device in the illustrated embodiment.

[0249] The explanations and beneficial effects of the relevant contents in any of the devices provided above can be found in the corresponding method embodiments provided above, and will not be repeated here.

[0250] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of apparatus or units may be electrical, mechanical, or other forms.

[0251] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. For example, the computer can be a personal computer, a server, or a network device, etc. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state disks, SSDs). For example, the aforementioned available media include, but are not limited to, USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, and other media capable of storing program code.

[0252] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A communication method, characterized in that, The method includes: Send a first request message to the second communication device. The first request message is used to request the relevant configuration information of the first communication device for data collection. Alternatively, the first request message is used to request the training dataset or model parameters on the side of the second communication device. The training dataset includes the dataset used by the second communication device to train the artificial intelligence AI model. The model parameters include the parameters of the AI ​​model after model training. Receive first configuration information or first data from the second communication device, wherein the first configuration information includes relevant configuration information for the first communication device to collect the data, and the first data includes training dataset or model parameters from the second communication device side; If it is determined that the first configuration information or the first data is lost, a second request message is sent to the second communication device according to the first information. The second request message is used to obtain the complete configuration information related to the data collection of the first communication device or the training dataset or model parameters on the side of the second communication device. The first information indicates the number of times and / or time information of sending the second request message.

2. The method according to claim 1, characterized in that, The first information indicates at least one of the following: The time interval between sending two consecutive request messages, wherein the two consecutive request messages include the first request message and the second request message; Should the request message be resent if the first configuration information or the first data is lost? The threshold corresponding to the number of times the request message is resent; The resent request message includes the second request message.

3. The method according to claim 2, characterized in that, The threshold includes a first threshold and a second threshold. The first threshold is the threshold corresponding to the number of times the request message is resent when the resent request message is used to request the training dataset on the second communication device side. The second threshold is the threshold corresponding to the number of times the request message is resent when the resent request message is used to request the model parameters on the second communication device side. The first threshold is less than the second threshold.

4. The method according to any one of claims 1 to 3, characterized in that, The first information is carried in a system message; or, The first piece of information is pre-configured.

5. The method according to claim 4, characterized in that, The system message originates from the central unit of the second communication device.

6. The method according to any one of claims 1 to 5, characterized in that, After sending a second request message to the second communication device based on the first information, the method further includes: Receive second configuration information or second data from the second communication device, wherein the second configuration information includes relevant configuration information for the first communication device to collect the data, and the second data includes training dataset or model parameters from the second communication device side; If it is determined that the second configuration information or the second data is not lost, a first indication message is sent to the second communication device, the first indication message indicating the end request.

7. The method according to any one of claims 1 to 5, characterized in that, If the first request message requests training datasets or model parameters from the second communication device, then after sending a second request message to the second communication device based on the first information, the method further includes: Receive second data from the second communication device, the second data including training dataset or model parameters from the second communication device side; If it is determined that the second data is lost, a second request message is sent to the second communication device. The second request message is used to request the retransmission of the training dataset or model parameters of the second communication device, or the second request message is used to request the missing data in the second data.

8. The method according to claim 7, characterized in that, The method further includes: If the number of times the second request message is sent reaches a threshold, a second indication message is sent to the second communication device, indicating that the request should be terminated.

9. The method according to claim 8, characterized in that, The method further includes: Send auxiliary information to the second communication device; If the second request message is used to request the training dataset on the side of the second communication device, the auxiliary information instructs the first communication device to use a portion of the data in the training dataset for model training; If the second request message is used to request model parameters from the second communication device, the auxiliary information indicates that the first communication device used some of the parameters in the model parameters. The auxiliary information also includes the values ​​of other parameters in the model parameters obtained by the first communication device training, excluding the partial parameters.

10. The method according to any one of claims 1 to 9, characterized in that, The first data includes N data blocks segmented at the radio resource control layer, where N is a positive integer. The method further includes: The system determines whether the first data is missing based on the identification information of the data block.

11. The method according to any one of claims 1 to 10, characterized in that, Sending the first request message to the second communication device includes: The first request message is sent to the distributed unit of the second communication device.

12. A communication method, characterized in that, The method includes: Receive a first request message from a first communication device. The first request message requests relevant configuration information for the first communication device to collect data. Alternatively, the first request message requests a training dataset or model parameters from the second communication device. The training dataset includes the dataset used by the second communication device to train an artificial intelligence (AI) model. The model parameters include the parameters of the AI ​​model after model training. Send first configuration information or first data to the first communication device. The first configuration information includes relevant configuration information for the first communication device to collect the data. The first data includes training dataset or model parameters from the second communication device side. The system receives a second request message from the first communication device. The second request message is used to obtain complete configuration information related to data collection by the first communication device or training dataset or model parameters on the side of the second communication device. The second request message is sent based on first information, which indicates the number of times and / or time information of sending the second request message.

13. The method according to claim 12, characterized in that, The first information indicates at least one of the following: The time interval between sending two consecutive request messages, wherein the two consecutive request messages include the first request message and the second request message; Should the request message be resent if the first configuration information or the first data is lost? The threshold corresponding to the number of times the request message is resent; The resent request message includes the second request message.

14. The method according to claim 13, characterized in that, The threshold includes a first threshold and a second threshold. The first threshold is the threshold corresponding to the number of times the request message is resent when the resent request message is used to request the training dataset on the second communication device side. The second threshold is the threshold corresponding to the number of times the request message is resent when the resent request message is used to request the model parameters on the second communication device side. The first threshold is less than the second threshold.

15. The method according to any one of claims 12 to 14, characterized in that, The first information is carried in a system message; or, The first piece of information is pre-configured.

16. The method according to claim 15, characterized in that, The system message originates from the central unit of the second communication device.

17. The method according to any one of claims 12 to 16, characterized in that, After receiving a second request message from the first communication device, the method further includes: Send second configuration information or second data to the first communication device. The second configuration information includes relevant configuration information for the first communication device to collect the data. The second data includes training dataset or model parameters on the side of the second communication device. Receive a first indication message from the first communication device, the first indication message indicating an end request, the first indication message being sent if the second configuration information or the second data is not lost.

18. The method according to any one of claims 12 to 16, characterized in that, If the first request message requests training datasets or model parameters from the second communication device, then after receiving the second request message from the first communication device, the method further includes: Send second data to the first communication device, the second data including the training dataset or model parameters on the side of the second communication device; The system receives a second request message from the first communication device, which requests the retransmission of the training dataset or model parameters of the second communication device, or requests the retransmission of missing data in the second data.

19. The method according to claim 18, characterized in that, The method further includes: Receive a second indication message from the first communication device, the second indication message indicating an end request; Release the configuration related to data collection by the first communication device according to the second instruction information.

20. The method according to claim 19, characterized in that, The method further includes: Receive auxiliary information from the first communication device; If the second request message requests the training dataset from the second communication device, the auxiliary information instructs the first communication device to use a portion of the data in the training dataset for model training. If the second request message requests model parameters from the second communication device, the auxiliary information indicates that the first communication device used some of the parameters in the model parameters. The auxiliary information also includes the values ​​of other parameters in the model parameters obtained by the first communication device training, excluding the partial parameters.

21. The method according to any one of claims 12 to 20, characterized in that, The first data includes N data blocks segmented at the radio resource control layer, where N is a positive integer.

22. The method according to any one of claims 12 to 21, characterized in that, Receiving the first request message from the first communication device includes: The first request message is received by the distributed unit of the second communication device.

23. A communication device, characterized in that, Includes modules or units for performing the method according to any one of claims 1 to 22.

24. A communication device, characterized in that, Includes a processor, the processor being configured to cause the communication device to perform the method of any one of claims 1 to 22.

25. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program or instructions that, when executed on a communication device, cause the communication device to perform the method as described in any one of claims 1 to 22.

26. A computer program product, characterized in that, The computer program product includes a computer program or instructions that, when executed on a communication device, cause the communication device to perform the method as described in any one of claims 1 to 22.

Images