Communication method, device and system

Abstract

The invention provides a communication method, device and system. The method can be applied to communication scenes such as an AI model training scene. In the method, the network equipment transmits data to the training device through the air interface, and leakage of private information of the network equipment is avoided. Besides, the network equipment classifies the training data to correspond to different training requirements and issue the corresponding training data for different training models, so that the complexity of acquiring the required data by the training device is further reduced, and the power consumption of the equipment is saved.

Description

Technical Field

[0001] This application relates to the field of communications. In particular, it relates to a communication method, apparatus, and system. Background Art

[0002] Machine learning is an important technical approach to realizing artificial intelligence (AI). For the training of an AI model on the user equipment (UE) side, the UE often triggers relevant data collection by itself. In order to train the AI model on the UE side, it is necessary to obtain the relevant configuration information of the input and output of the AI model to associate different AI models with different configurations. However, such information has the disadvantage of exposing the private information of the network side because it involves how the network side configures the input information for different AI models. Summary of the Invention

[0003] This application provides a communication method, apparatus, and system that can avoid the leakage of privacy information of network devices.

[0004] In a first aspect, a communication method is provided. This method can be executed by a first training device, or can also be executed by a chip or circuit for the first training device. This application does not make any limitations in this regard. For ease of description, the following takes the execution by the first training device as an example for illustration.

[0005] The method includes: receiving first data from a first network device, where the first data belongs to at least one data set, and the at least one data set is used for the training of at least one AI model; training a first AI model based on the first data, where the first AI model belongs to the at least one AI model.

[0006] In this method, the network device transmits data to the training device through the air interface, avoiding the leakage of the private information of the network device.

[0007] In some implementation manners, the first data is the input data of the first training device, the second data is the input data of the second training device, the first data is different from the second data, and the AI models corresponding to the first training device and the second training device have the same function.

[0008] In this manner, the data corresponding to different training devices is different, and multiple training devices can synchronously receive the data required for the same AI model, improving the data reception efficiency.

[0009] In some implementation manners, send first information to the first network device, where the first information indicates the feature information of the first training device, and / or the first information indicates the feature information of the first AI model.

[0010] In this method, the training device reports feature information to the network device, making it easier for the network device to allocate data based on the feature information, reducing the complexity of data allocation by the network device, and at the same time establishing a strong correspondence between the data and the AI model, thereby improving training efficiency.

[0011] In certain implementations, the characteristic information of the first training device includes identification information and / or computing power information of the first training device, and the characteristic information of the first AI model includes at least one of the purpose of the first AI model, identification information of the first AI model, the type of data required by the first AI model, or the size of the data required by the first AI model.

[0012] In some implementations, second information is sent to the first network device, where the second information indicates that the data received by the first training device is sufficient for training the first AI model, or the second information indicates that the data received by the first training device is insufficient for training the first AI model.

[0013] In this manner, the training device can provide feedback to the network device on whether the received data is sufficient to complete the training, so that the network device can obtain the data transmission status in a timely manner.

[0014] In some implementations, the second information further indicates a progress of receiving the first data.

[0015] In some implementations, third information is received, the third information indicating an end of the first data transmission.

[0016] In this manner, the network device notifies the training device after the data transmission is completed, so that the training device can stop receiving data in time, further saving the power consumption of the training device.

[0017] In a second aspect, a communication method is provided. The method may be executed by a first network device, or may be executed by a chip or circuit used for the first network device, which is not limited in this application. For ease of description, the following description is based on an example of execution by the first network device.

[0018] The method includes: obtaining first data, the first data belonging to at least one data set, the at least one data set being used for training at least one AI model, the first data being used for training a first AI model, the first AI model belonging to the at least one AI model;

[0019] First data is sent to a first training device.

[0020] In some implementations, second data is sent to a second training device, where the second data is different from the first data, and the first training device has the same function as the AI model corresponding to the second training device.

[0021] In some implementations, first information is received from the first training device, where the first information indicates the feature information of the first training device, or the first information indicates the feature information of the first AI model.

[0022] In some implementations, the feature information of the first training device includes the identification information and / or computing power information of the first training device, and the feature information of the first AI model includes at least one of the purpose of the first AI model, the identification information of the first AI model, the type of data required by the first AI model, or the size of the data required by the first AI model.

[0023] In some implementations, the first data is determined from the at least one data set according to the first information.

[0024] In some implementations, N first information is received from N training devices, where the N first information respectively indicates the feature information of the N training devices, or the N first information indicates the feature information of M AI models. Determining the first data includes: determining the size of the first data according to the number of the first information corresponding to the first AI model and the total amount of data corresponding to the first AI model.

[0025] In some implementations, second information is received from the first training device, where the second information indicates that the first training device has received the amount of data required for training the first AI model, or has not received the amount of data required for training the first AI model.

[0026] In some implementations, the second information further indicates the reception progress of the first data.

[0027] In some implementations, third information is sent to the first training device, where the third information indicates the end of the transmission of the first data.

[0028] In some implementations, fourth information is sent to a second network device, where the fourth information indicates the feature information of the N training devices, or the feature information of the M first AI models.

[0029] In this way, the first network device reports the feature information to the second network device, which is convenient for the second network device to perform data allocation.

[0030] In some implementations, receive fifth information from the second network device, where the fifth information indicates the size of the first data, and the size of the first data is determined according to the total amount of data corresponding to the first AI model and the N; obtain the first data according to the fifth information.

[0031] In a third aspect, a communication method is provided. This method can be executed by a second network device, or can be executed by a chip or circuit for the second network device. This application does not make a limitation in this regard. For ease of description, the following takes the execution by the second network device as an example for illustration.

[0032] The method includes: receiving fourth information, where the fourth information indicates the feature information of N training devices, or the feature information of M first AI models, and the first AI model belongs to at least one type of AI model; determining first data according to the fourth information and at least one data set, where the at least one data set is used for training at least one type of AI model, and the first data is used for training the first AI model.

[0033] In some implementations, determining first data according to the fourth information and at least one data set includes: determining the size of the first data according to the total amount of data corresponding to the first AI model and the N, and the data corresponding to the first AI model belongs to the at least one data set.

[0034] In some implementations, send fifth information, where the fifth information indicates the size of the first data.

[0035] In a fourth aspect, a communication device is provided, including a transceiver module and a processing module. The transceiver module is used to receive first data from a first network device, and the first data belongs to at least one data set, and the at least one data set is used for training at least one artificial intelligence (AI) model; the processing module is used to train a first AI model based on the first data, and the first AI model belongs to the at least one type of AI model.

[0036] In some implementations, the first data is the input data of a first training device, the second data is the input data of a second training device, the first data is different from the second data, and the functions of the AI models corresponding to the first training device and the second training device are the same.

[0037] In some implementations, the transceiver module is used to send first information to the first network device, where the first information indicates the feature information of the first training device, and / or the first information indicates the feature information of the first AI model.

[0038] In some implementations, the feature information of the first training device includes the identification information and / or computing power information of the first training device, and the feature information of the first AI model includes at least one of the purpose of the first AI model, the identification information of the first AI model, the type of data required by the first AI model, or the size of the data required by the first AI model.

[0039] In some implementations, the transceiver module is used to send second information to the first network device, where the second information indicates that the data received by the first training device is sufficient for the training of the first AI model, or the second information indicates that the data received by the first training device is insufficient for the training of the first AI model.

[0040] In some implementations, the second information further indicates the reception progress of the first data.

[0041] In some implementations, the transceiver module is used to receive third information, where the third information indicates the end of the first data transmission.

[0042] In a fifth aspect, a communication device is provided, including a transceiver module and a processing module. The processing module is used to obtain first data, where the first data belongs to at least one data set, the at least one data set is used for the training of at least one AI model, the first data is used to train a first AI model, and the first AI model belongs to the at least one AI model; the transceiver module is used to send the first data to the first training device.

[0043] In some implementations, the transceiver module is used to send second data to a second training device, where the second data is different from the first data, and the AI models corresponding to the first training device and the second training device have the same function.

[0044] In some implementations, the transceiver module is used to receive first information from the first training device, where the first information indicates the feature information of the first training device, or the first information indicates the feature information of the first AI model.

[0045] In some implementations, the feature information of the first training device includes the identification information and / or computing power information of the first training device, and the feature information of the first AI model includes at least one of the purpose of the first AI model, the identification information of the first AI model, the type of data required by the first AI model, or the size of the data required by the first AI model.

[0046] In some implementations, the processing module is used to determine the first data from the at least one data set according to the first information.

[0047] In some implementations, the processing module is configured to receive N pieces of first information from N training devices, where the N pieces of first information respectively indicate the feature information of the N training devices, or the N pieces of first information indicate the feature information of M AI models. The processing module is configured to determine the size of the first data according to the number of pieces of first information corresponding to the first AI model and the total amount of data corresponding to the first AI model.

[0048] In some implementations, the transceiver module is configured to receive second information from the first training device, where the second information indicates that the first training device has received the amount of data required for training the first AI model, or has not received the amount of data required for training the first AI model.

[0049] In some implementations, the second information further indicates the reception progress of the first data.

[0050] In some implementations, the transceiver module is configured to send third information to the first training device, where the third information indicates the end of the transmission of the first data.

[0051] In some implementations, the transceiver module is configured to send fourth information to a second network device, where the fourth information indicates the feature information of the N training devices, or the feature information of the M first AI models.

[0052] In some implementations, the transceiver module is configured to receive fifth information from the second network device, where the fifth information indicates the size of the first data, and the size of the first data is determined according to the total amount of data corresponding to the first AI model and the N; the processing module is configured to obtain the first data according to the fifth information.

[0053] In a sixth aspect, a communication device is provided, including a transceiver module and a processing module. The transceiver module is configured to receive fourth information, where the fourth information indicates the feature information of N training devices, or the feature information of M first AI models, and the first AI model belongs to at least one type of AI model; the processing module is configured to determine first data according to the fourth information and at least one data set, where the at least one data set is used for the training of at least one type of AI model, and the first data is used for the training of the first AI model.

[0054] In some implementations, the processing module is configured to determine the size of the first data according to the total amount of data corresponding to the first AI model and the N, and the data corresponding to the first AI model belongs to the at least one data set.

[0055] In some implementations, the transceiver module is configured to send fifth information, where the fifth information indicates the size of the first data.

[0056] It should be understood that the fourth, fifth, and sixth aspects are the implementation manners on the device side corresponding to the first, second, and third aspects. The descriptions of the explanations, supplements, and beneficial effects of the first, second, and third aspects also apply to the fourth, fifth, and sixth aspects, and will not be elaborated herein.

[0057] In a seventh aspect, the present application provides a communication device, including an interface circuit and a processor. The interface circuit is used to implement the functions of the transceiver module in the fourth aspect, and the processor is used to implement the functions of the processing module in the third aspect.

[0058] In an eighth aspect, the present application provides a communication device, including an interface circuit and a processor. The interface circuit is used to implement the functions of the transceiver module in the fifth aspect, and the processor is used to implement the functions of the processing module in the fourth aspect.

[0059] In a ninth aspect, the present application provides a communication device, including an interface circuit and a processor. The interface circuit is used to implement the functions of the transceiver module in the sixth aspect, and the processor is used to implement the functions of the processing module in the fourth aspect.

[0060] In a tenth aspect, the present application provides a computer-readable medium, which stores program codes for a training device to execute. The program codes include instructions for executing the method of the first aspect, or any possible manner in the first aspect, or all possible manners in the first aspect.

[0061] In an eleventh aspect, an embodiment of the present application provides a computer-readable medium, which stores program codes for a network device to execute. The program codes include instructions for executing the method of the second aspect, or the third aspect, or any possible manner in the second aspect, or any possible manner in the third aspect, or all possible manners in the second aspect, or all possible manners in the third aspect.

[0062] In a twelfth aspect, a computer program product storing computer-readable instructions is provided. When the computer-readable instructions run on a computer, the computer is caused to execute the method of the first aspect, or any possible manner in the first aspect, or all possible manners in the first aspect.

[0063] In a thirteenth aspect, a computer program product storing computer-readable instructions is provided. When the computer-readable instructions run on a computer, the computer is caused to execute the method of the above-mentioned second aspect, or the third aspect, or any possible manner in the second aspect, or any possible manner in the third aspect, or all possible manners in the second aspect, or all possible manners in the third aspect.

[0064] In a fourteenth aspect, a communication system is provided. The communication system includes a device having methods implementing the above-mentioned first aspect, or any possible manner in the first aspect, or all possible manners in the first aspect, the second aspect, or the third aspect, or any possible manner in the second aspect, or any possible manner in the third aspect, or all possible manners in the second aspect, or all possible manners in the third aspect, and functions of various possible designs.

[0065] In a fifteenth aspect, a processor is provided for coupling with a memory and for executing the method of the above-mentioned first aspect, or any possible manner in the first aspect, or all possible manners in the first aspect.

[0066] In a sixteenth aspect, a processor is provided for coupling with a memory and for executing the method of the second aspect, or the third aspect, or any possible manner in the second aspect, or any possible manner in the third aspect, or all possible manners in the second aspect, or all possible manners in the third aspect.

[0067] In a seventeenth aspect, a chip system is provided. The chip system includes a processor and may further include a memory for executing a computer program or instruction stored in the memory, so that the chip system implements the method in any one of the foregoing first aspect, second aspect, or third aspect, and any possible implementation manner of any aspect. The chip system may be composed of chips or may include chips and other discrete devices.

[0068] In an eighteenth aspect, a communication method is provided, including: a first network device obtains first data, the first data belongs to at least one data set, the at least one data set is used for training of at least one AI model, the first data is used for training a first AI model, and the first AI model belongs to the at least one AI model; the first network device sends the first data to a first training device; the first training device trains the first AI model based on the first data, and the first AI model belongs to the at least one AI model.

[0069] In a nineteenth aspect, a communication method is provided, including: a second network device receives fourth information from a first network device, where the fourth information indicates the feature information of N training devices or the feature information of M first AI models, and the first AI models belong to at least one type of AI model; the second network device determines first data according to the fourth information and at least one data set, where the at least one data set is used for the training of at least one type of AI model, and the first data is used for training a first AI model; the first network device obtains the first data, where the first data belongs to at least one data set, the at least one data set is used for the training of at least one type of AI model, the first data is used for training a first AI model, and the first AI model belongs to the at least one type of AI model; the first network device sends the first data to a first training device; the first training device trains the first AI model based on the first data, and the first AI model belongs to the at least one type of AI model. Description of the Drawings

[0070] Figure 1 is a schematic diagram of a possible application framework in a communication system;

[0071] Figure 2 is another schematic diagram of a possible application framework in a communication system;

[0072] Figure 3 is a schematic diagram of a communication system applicable to an embodiment of the present application;

[0073] Figure 4 is a schematic diagram of another communication system applicable to an embodiment of the present application;

[0074] Figure 5 is a schematic block diagram of an autoencoder;

[0075] Figure 6 is a schematic diagram of an AI application framework;

[0076] Figure 7 is a schematic diagram of a communication method provided by an embodiment of the present application;

[0077] Figure 8 is a schematic diagram of a communication process provided by an embodiment of the present application;

[0078] Figure 9 is a schematic diagram of another communication process provided by an embodiment of the present application;

[0079] Figure 10 is a schematic block diagram of a communication device;

[0080] Figure 11 is a schematic block diagram of another communication device;

[0081] Figure 12 It is a schematic block diagram of another communication device. Detailed implementation manners

[0082] Next, the technical solutions in the present application will be described with reference to the accompanying drawings.

[0083] The technical solutions provided in the present application can be applied to various communication systems, such as: the fifth generation (5G) or new radio (NR) system, the long term evolution (LTE) system, the LTE frequency division duplex (FDD) system, the LTE time division duplex (TDD) system, the wireless local area network (WLAN) system, the satellite communication system, future communication systems, such as the sixth generation (6G) mobile communication system, or a fusion system of multiple systems, etc. The technical solutions provided in the present 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 the Internet of Things (IoT) communication system or other communication systems.

[0084] A network element in a communication system can send a signal to another network element or receive a signal from another network element. The signal can include information, signaling, data, etc. Herein, the network element can also be replaced with an entity, a network entity, a device, a communication device, a communication module, a node, a communication node, etc. In the present disclosure, the description is made by taking the network element as an example. For example, a communication system can include at least one terminal device and at least one network device. The network device can send a downlink signal to the terminal device, and / or the terminal device can send an uplink signal to the network device. It can be understood that the terminal device in the present disclosure can be replaced with a first network element, and the network device can be replaced with a second network element, and the two execute the corresponding communication methods in the present disclosure.

[0085] In the embodiments of the present application, the terminal device can also be referred to as a user equipment (UE), an access terminal, a user unit, a user station, a mobile station, a mobile device, a remote station, a remote terminal, a mobile device, a user terminal, a terminal, a wireless communication device, a user agent, or a user device.

[0086] The terminal device can be a device that provides voice / data. For example, it can be a handheld device, a vehicle-mounted device, etc. with wireless connection capabilities. Currently, some examples of terminals are: mobile phone, tablet computer, laptop computer, palmtop computer, mobile internet device (MID), wearable device, virtual reality (VR) device, augmented reality (AR) device, wireless terminal in industrial control, wireless terminal in self-driving, wireless terminal in remote medical surgery, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, cellular phone, cordless phone, session initiation protocol (SIP) phone, wireless local loop (WLL) station, personal digital assistant (PDA), a handheld device with wireless communication capabilities, a computing device, or other processing devices connected to a wireless modem, wearable device, terminal device in a 5G network, or terminal device in a future evolved public land mobile network (PLMN), etc. The embodiments of this application are not limited thereto.

[0087] By way of example and not limitation, in the embodiments of this application, the terminal device can also be a wearable device. A wearable device can also be referred to as a wearable intelligent device, which is a general term for devices developed by applying wearable technology to the intelligent design of daily wear, such as glasses, gloves, watches, clothing, and shoes, etc. A wearable device is a portable device that is either directly worn on the body or integrated into the user's clothes or accessories. A wearable device is not just a hardware device, but more importantly, it realizes powerful functions through software support, data interaction, and cloud interaction. Generally, wearable intelligent devices include those with complete functions and large sizes that can achieve complete or partial functions without relying on a smartphone, such as smart watches or smart glasses, etc., and those that only focus on a certain type of application function and need to cooperate with other devices such as smartphones, such as various smart bracelets and smart jewelry for physical sign monitoring.

[0088] In the embodiments of the present application, the device for implementing the functions of the terminal device may be the terminal device itself, or a device capable of supporting the terminal device to implement such functions, such as a chip system. This device may be installed in the terminal device or used in conjunction with the terminal device. In the embodiments of the present application, the chip system may be composed of chips, or may include chips and other discrete devices. In the embodiments of the present application, only the case where the device for implementing the functions of the terminal device is the terminal device is used as an example for illustration, which does not limit the solutions of the embodiments of the present application.

[0089] The network device in the embodiments of the present application can be a device for communicating with a terminal device. This network device can also be referred to as an access network device or a radio access network device. For example, the network device can be a base station. The network device in the embodiments of the present application can refer to a radio access network (RAN) node (or device) that connects a terminal device to a wireless network. A base station can generally cover various names as follows, or be replaced with the following names, such as: Node B, evolved Node B (eNB), next generation Node B (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master station, slave station, multi-mode 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), radio unit (RU), positioning node, etc. A base station can be a macro base station, a micro base station, a relay node, a donor node, or the like, or a combination thereof. A base station can also refer to a communication module, a modem, or a chip disposed in the foregoing device or apparatus. A base station can also be a mobile switching center and a device that undertakes the function of a base station in D2D, V2X, M2M communications, a network-side device in a 6G network, a device that undertakes the function of a base station in a future communication system, etc. A base station can support networks with the same or different access technologies. Optionally, the RAN node can also be a server, a wearable device, a vehicle, or an in-vehicle device, etc. For example, the access network device in vehicle to everything (V2X) technology can be a road side unit (RSU). The embodiments of the present application do not limit the specific technologies and specific device forms adopted by the network device.

[0090] A base station can be fixed or mobile. For example, a helicopter or a drone can be configured to act as a mobile base station, and one or more cells can move according to the position of the mobile base station. In other examples, a helicopter or a drone can be configured to be used as a device for communicating with another base station.

[0091] In some deployments, the network device mentioned in the embodiments of the present application may be a device including a CU, or a DU, or a device including a CU and a DU, or a control plane CU node (central unit-control plane, CU-CP) and a user plane CU node (central unit-user plane, CU-UP) and a DU node. For example, the network device may include a gNB-CU-CP, a gNB-CU-UP, and a gNB-DU.

[0092] In some deployments, multiple RAN nodes cooperate to assist a terminal in achieving wireless access, and different RAN nodes respectively implement partial functions of a base station. For example, the RAN node may be a CU, a DU, a CU-CP, a CU-UP, or an RU, etc. The CU and the DU may be separately provided, or may also be included in the same network element, such as a BBU. The RU may be included in a radio frequency device or a radio frequency unit, such as being included in an RRU, an AAU, or an RRH.

[0093] RAN nodes can support one or more types of fronthaul interfaces. Different fronthaul interfaces respectively correspond to DUs and RUs with different functions. If the fronthaul interface between the DU and the RU is the common public radio interface (CPRI), the DU is configured to implement one or more of the baseband functions, and the RU is configured to implement one or more of the radio frequency functions. If the fronthaul interface between the DU and the RU is another interface, compared with CPRI, some of the downlink and / or uplink baseband functions, for example, for the downlink, one or more of precoding, digital beamforming (BF), or inverse fast Fourier transform (IFFT) / cyclic prefix (CP) addition, are moved from the DU to the RU for implementation; for the uplink, one or more of digital beamforming (BF), or fast Fourier transform (FFT) / cyclic prefix (CP) removal, are moved from the DU to the RU for implementation. In a possible implementation, this interface can be the enhanced common public radio interface (eCPRI). Under the eCPRI architecture, different splitting methods between the DU and the RU correspond to different categories (Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, F.

[0094] Taking eCPRI Cat A as an example, for downlink transmission, with layer mapping as the segmentation, the DU is configured to implement one or more functions before layer mapping (i.e., one or more of encoding, rate matching, scrambling, modulation, and layer mapping), while other functions after layer mapping (such as one or more of resource element (RE) mapping, digital beamforming (BF), or inverse fast Fourier transform (IFFT) / adding cyclic prefix (CP)) are moved to the RU for implementation. For uplink transmission, with de-RE mapping as the segmentation, the DU is configured to implement one or more functions before demapping (i.e., one or more of decoding, derate matching, descrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and de-RE mapping), while other functions after demapping (such as one or more of digital BF or fast Fourier transform (FFT) / removing CP) are moved to the RU for implementation. It can be understood that for the function descriptions of the DU and RU corresponding to various types of eCPRI, reference can be made to the eCPRI protocol and will not be elaborated here.

[0095] In a possible design, the processing unit in the BBU for implementing baseband functions is called the baseband high (BBH) unit, and the processing unit in the RRU / AAU / RRH for implementing baseband functions is called the baseband low (BBL) unit.

[0096] In different systems, the CU (or CU-CP and CU-UP), DU, or RU may also have different names, but those skilled in the art can understand their meanings. For example, in the ORAN system, the CU can also be called O-CU (open CU), the DU can also be called O-DU, the CU-CP can also be called O-CU-CP, the CU-UP can also be called O-CU-UP, and the RU can also be called O-RU. Any one of the 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.

[0097] In the embodiments of the present application, the device for implementing the functions of a network device may be a network device; or it may be a device capable of supporting the network device to implement such functions, such as a chip system, a hardware circuit, a software module, or a combination of a hardware circuit and a software module. This device may be installed in the network device or used in matching with the network device. In the embodiments of the present application, only the case where the device for implementing the functions of a network device is a network device is taken as an example for illustration, which does not limit the solutions of the embodiments of the present application.

[0098] The network device and / or the terminal device may be deployed on land, including indoor or outdoor, handheld or vehicle-mounted; may also be deployed on water; or may be deployed on aircraft, balloons, and satellites in the air. In the embodiments of the present application, the scenarios where the network device and the terminal device are located are not limited. In addition, the terminal device and the network device may be hardware devices, or may be software functions running on dedicated hardware or software functions running on general hardware. For example, they may be virtualized functions instantiated on a platform (such as a cloud platform), or may be entities including dedicated or general hardware devices and software functions. The present application does not limit the specific forms of the terminal device and the network device.

[0099] In a wireless communication network, for example, in a mobile communication network, the services supported by the network are becoming more and more diverse, so the requirements to be met are becoming more and more diverse. For example, the network needs to be able to support ultra-high rate, ultra-low latency, and / or ultra-large connection. This feature makes network planning, network configuration, and / or resource scheduling more and more complex. In addition, due to the increasing powerful functions of the network, such as supporting higher and higher frequencies, supporting high-order multiple input multiple output (MIMO) technology, supporting beamforming, and / or supporting new technologies such as beam management, network energy saving has become a hot research topic. These new requirements, new scenarios, and new features have brought unprecedented challenges to network planning, operation and maintenance, and efficient operation. To meet this challenge, artificial intelligence technology can be introduced into the wireless communication network to achieve network intelligence.

[0100] To support AI technology in the wireless network, AI nodes may also be introduced into the network.

[0101] Optionally, the AI node may be deployed at one or more of the following positions in the communication system: an access network device, a terminal device, or a core network device, etc. Or, the AI node may also be deployed independently. For example, it may be deployed at a position outside any of the above devices, such as in the host of an over the top (OTT) system or a cloud server. The AI node can communicate with other devices in the communication system. Other devices may be, for example, one or more of the following: a network device, a terminal device, or a network element of the core network.

[0102] It can be understood that the number of AI nodes in this application is not limited. For example, when there are multiple AI nodes, the multiple AI nodes can be divided based on functions. For example, different AI nodes are responsible for different functions.

[0103] It can also be understood that the AI nodes can be independent devices respectively, or can be integrated in the same device to implement different functions, or can be network elements in hardware devices, or can be software functions running on dedicated hardware, or can be virtualized functions instantiated on a platform (such as a cloud platform). This application does not limit the specific form of the above AI nodes.

[0104] The AI node can be an AI network element or an AI module.

[0105] Figure 1 It is a schematic diagram of a possible application framework in a communication system. As Figure 1 shown, the network elements in the communication system are connected through interfaces (such as NG, Xn) or the air interface. One or more AI modules are provided in one or more of these network element nodes, such as core network devices, access network nodes (RAN nodes), terminals, or OAM. (For clarity, Figure 1 only 1 is shown). The access network node can be a separate RAN node or can include multiple RAN nodes. For example, it includes a CU and a DU. One or more AI modules can also be provided in the CU and / or the DU. Optionally, the CU can also be split into a CU-CP and a CU-UP. One or more AI models are provided in the CU-CP and / or the CU-UP.

[0106] The AI module is used to implement the corresponding AI function. The AI modules deployed in different network elements can be the same or different. According to different parameter configurations of the model of the AI module, the AI module can implement different functions. The model of the AI module can be configured based on one or more of the following parameters: structural parameters (such as at least one of the number of neural network layers, the width of the neural network, the connection relationship between layers, the weights of neurons, the activation function of neurons, or the bias in the activation function), input parameters (such as the type and / or dimension of the input parameters), or output parameters (such as the type and / or dimension of the output parameters). Among them, the bias in the activation function can also be called the bias of the neural network.

[0107] An AI module can have one or more models. One model can infer an output, and the output includes one parameter or multiple parameters. The learning process, training process, or inference process of different models can be deployed in different nodes or devices, or can be deployed in the same node or device.

[0108] Figure 2Schematic diagram of a possible application framework in a communication system. As Figure 2 shown, the communication system includes a RAN intelligent controller (RIC). For example, the RIC can be Figure 1 the AI modules 117, 118 shown in

[0109] to implement AI-related functions. The RIC includes a near-real time RIC and a non-real time RIC. Among them, the non-real time RIC mainly processes non-real time information, such as data that is not sensitive to latency, and the latency of this data can be in seconds. The real-time RIC mainly processes near-real time information, such as data that is relatively sensitive to latency, and the latency of this data is in tens of milliseconds.

[0110] The near-real time RIC is used for model training and inference. For example, it is used to train an AI model and perform inference using this AI model. The near-real time RIC can obtain network-side and / or terminal-side information from RAN nodes (such as CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or inference data. Optionally, the near-real time RIC can submit the inference result to the RAN node and / or the terminal. Optionally, the inference result can be exchanged between the CU and the DU, and / or between the DU and the RU. For example, the near-real time RIC submits the inference result to the DU, and the DU sends it to the RU.

[0111] The near-real time RIC and the non-real time RIC can also be separately set as a network element. Optionally, the near-real time RIC and the non-real time RIC can also be part of other devices. For example, the near-real time RIC is set in a RAN node (such as in the CU or DU), and the non-real time RIC is set in the OAM, cloud server, core network device, or other network devices.

[0112] Figure 3 Schematic diagram of a communication system applicable to the communication method of the embodiments of the present application. AsFigure 3 As shown, the communication system 100 may include at least one network device, such as Figure 3 the network device 110 shown; the communication system 100 may further include at least one terminal device, such as Figure 3 the terminal devices 120 and 130 shown. The network device 110 and the terminal devices (such as the terminal devices 120 and 130) may communicate via a wireless link. Among the communication devices in this communication system, for example, between the network device 110 and the terminal device 120, communication may be carried out via multi-antenna technology.

[0113] Figure 4 is a schematic diagram of another communication system applicable to the communication method of the embodiments of the present application. Compared with Figure 3 the communication system 100 shown, Figure 4 the communication system 200 shown further includes an AI network element 140. The AI network element 140 is used to perform AI-related operations, such as constructing a training data set or training an AI model, etc.

[0114] In a possible implementation manner, the network device 110 may send data related to the training of the AI model to the AI network element 140, and the AI network element 140 constructs a training data set and trains the AI model. For example, the data related to the training of the AI model may include the data reported by the terminal device. The AI network element 140 may send the results of the operations related to the AI model to the network device 110, and forward them to the terminal device through the network device 110. For example, the results of the operations related to the AI model may include at least one of the following: the trained AI model, the evaluation result or the test result of the model, etc. Exemplarily, a part of the trained AI model may be deployed on the network device 110, and another part may be deployed on the terminal device. Alternatively, the trained AI model may be deployed on the network device 110. Or, the trained AI model may be deployed on the terminal device.

[0115] It should be understood that Figure 4 only the case where the AI network element 140 is directly connected to the network device 110 is taken as an example for illustration. In other scenarios, the AI network element 140 may also be connected to the terminal device. Or, the AI network element 140 may be connected to both the network device 110 and the terminal device at the same time. Or, the AI network element 140 may also be connected to the network device 110 through a third-party network element. The embodiments of the present application do not limit the connection relationship between the AI network element and other network elements.

[0116] The AI network element 140 may also be set as a module in the network device and / or the terminal device. For example, it may be set in Figure 3 the network device 110 or the terminal device shown.

[0117] It should be noted that, Figure 3 and Figure 4 are simplified schematic diagrams shown for the convenience of understanding. For example, the communication system may further include other devices, such as wireless relay devices and / or wireless backhaul devices, etc., Figure 3 and Figure 4 which are not drawn in. In practical applications, the communication system may include multiple network devices or multiple terminal devices. The embodiments of the present application do not limit the number of network devices and terminal devices included in the communication system.

[0118] To facilitate the understanding of the solutions of the embodiments of the present application, the following terms that may be involved in the embodiments of the present application are explained.

[0119] 1. Artificial intelligence: It means enabling a machine to have the ability to learn, accumulate experience, and solve problems that humans can solve through experience, such as natural language understanding, image recognition, and playing chess. Artificial intelligence can be understood as the intelligence demonstrated by a machine made by humans. Generally, artificial intelligence refers to the technology that presents human intelligence through computer programs. The goals of artificial intelligence include understanding intelligence by constructing computer programs with symbolic reasoning or inference.

[0120] 2. Machine learning: It is an implementation method of artificial intelligence. Machine learning is a method that can endow a machine with the ability to learn, so that the machine can complete functions that cannot be completed by direct programming. In a practical sense, machine learning is a method of training a model by using data and then using the model for prediction. There are many machine learning methods, such as neural network (NN), decision tree, support vector machine, etc. Machine learning theory mainly designs and analyzes some algorithms that allow a computer to automatically learn. Machine learning algorithms are a class of algorithms that automatically analyze and obtain rules from data and use the rules to predict unknown data.

[0121] 3. Neural network: It is a specific embodiment of machine learning methods. A neural network is a mathematical model that mimics the behavioral characteristics of the animal neural network for information processing. The idea of the neural network comes from the neuron structure of the brain tissue. Each neuron can perform a weighted summation operation on its input value, and the result of the weighted summation operation is output through an activation function.

[0122] A neural network generally includes a multi-layer structure. Each layer may include one or more logical judgment units, which can be referred to as neurons. By increasing the depth and / or width of the neural network, the expressive power of the neural network can be improved, providing a more powerful information extraction and abstract modeling ability for complex systems. Among them, the depth of the neural network can be understood as the number of layers included in the neural network, and the number of neurons included in each layer can be called the width of that layer. In one possible implementation, the neural network includes an input layer and an output layer. After the input received by the input layer of the neural network is processed by neurons, the result is passed to the output layer, and the output result of the neural network is obtained by the output layer. In another possible implementation, the neural network includes an input layer, a hidden layer, and an output layer. After the input received by the input layer of the neural network is processed by neurons, the result is passed to the intermediate hidden layer, and the hidden layer then passes the calculation result to the output layer or the adjacent hidden layer, and finally the output result of the neural network is obtained by the output layer. A neural network may include one or more sequentially connected hidden layers without limitation.

[0123] During the training process of the neural network, a loss function can be defined. The loss function is used to measure the difference between the predicted value and the true value of the model. During the training process of the neural network, the loss function describes the gap or difference between the output value of the neural network and the ideal target value. The training process of the neural network is a process of adjusting the neural network parameters so that the value of the loss function is less than the threshold value or meets the target requirements. Among them, the neural network parameters may include at least one of the following: the number of layers of the neural network, the width, the weights of the neurons, and the parameters in the activation function of the neurons.

[0124] Taking the type of the AI model as a neural network as an example, the AI model involved in the present disclosure may be a deep neural network (DNN). According to the construction method of the network, DNNs may include feedforward neural networks (FNNs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs), etc.

[0125] 4. Deep neural network: A neural network with multiple hidden layers.

[0126] 5. Deep learning: Machine learning using deep neural networks.

[0127] 6. AI model:

[0128] An AI model is an algorithm or computer program that can implement AI functions, and the AI model represents the mapping relationship between the input and output of the model. The types of AI models can be neural networks, linear regression models, decision tree models, support vector machines (SVMs), Bayesian networks, Q-learning models, or other machine learning (ML) models.

[0129] Exemplarily, the AI model in the embodiments of the present application may include an encoder and a decoder. The encoder and the decoder are used in a matching manner. It can be understood that the encoder and the decoder are a set of supporting AI models. The encoder and the decoder can be respectively deployed on a terminal device and a network device. In a possible design, a set of matching encoder and decoder can specifically be two parts in the same auto-encoder (AE), for example, as Figure 5 shown. The AE model with the encoder and the decoder respectively deployed on different nodes is a typical bilateral model. The encoder and the decoder of the AE model are usually co-trained and used in a matching manner. The encoder processes the input V to obtain the processed result z, and the decoder can decode the output z of the encoder into the desired output V'.

[0130] Alternatively, the AI model in the embodiments of the present application can be a single-end model, and the AI model can be deployed on a terminal device or a network device.

[0131] 7. Training data set and inference data:

[0132] In the field of machine learning, the ground truth usually refers to the data that is considered accurate or real data.

[0133] The training data set is used for training the AI model. The training data set can include the input of the AI model, or include the input and target output of the AI model. Among them, the training data set includes one or more training data, and the training data can include the training samples input to the AI model, or can also include the target output of the AI model. Among them, the target output can also be referred to as a label, sample label, or labeled sample. The label is the ground truth.

[0134] In the field of communication, the training data set can include simulation data collected through a simulation platform, or experimental data collected from experimental scenarios, or measured data collected in an actual communication network. Due to differences in the geographical environment and channel conditions where the data is generated, such as differences in indoor, outdoor, moving speed, frequency band, or antenna configuration, etc., when obtaining data, the collected data can be classified. For example, data with the same channel propagation environment and antenna configuration can be grouped into one category.

[0135] Model training essentially involves learning certain features from the training data. In the process of training an AI model (such as a neural network model), since it is desired that the output of the AI model is as close as possible to the value that is truly wanted to be predicted, the weight vector of each layer of the AI model can be updated by comparing the predicted value of the current network with the truly desired target value, and then according to the difference between the two. (Of course, there is usually an initialization process before the first update, that is, parameters are pre-configured for each layer in the AI model). For example, if the predicted value of the network is high, the weight vector is adjusted to make it predict lower, and continuous adjustment is made until the AI model can predict the truly desired target value or a value very close to the truly desired target value. Therefore, it is necessary to pre-define "how to compare the difference between the predicted value and the target value", which is the loss function or objective function, and they are important equations for measuring the difference between the predicted value and the target value. Among them, taking the loss function as an example, the higher the output value (loss) of the loss function, the greater the difference. Then the training of the AI model becomes a process of minimizing this loss as much as possible, so that the value of the loss function is less than the threshold, or the value of the loss function meets 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 of the neural network, the width, the weights of the neurons, or the parameters in the activation function of the neurons.

[0136] Inference data can be used as the input of a trained AI model for inference of the AI model. During the model inference process, when the inference data is input into the AI model, the corresponding output, which is the inference result, can be obtained.

[0137] 8. Design of AI Model:

[0138] The design of the AI model mainly includes a data collection link (such as collecting training data and / or inference data), a model training link, and a model inference link. Further, it can also include an inference result application link.

[0139] Figure 6 An AI application framework is shown.

[0140] In the foregoing data collection phase, the data source is used to provide the training data set and the inference data. In the model training phase, the AI model is obtained by analyzing or training the training data provided by the data source. Among them, the AI model represents the mapping relationship between the input and output of the model. Obtaining the AI model through the model training node is equivalent to learning the mapping relationship between the input and output of the model using the training data. In the model inference phase, the AI model trained in the model training phase is used to perform inference based on the inference data provided by the data source to obtain the inference result. This phase can also be understood as: inputting the inference data into the AI model and obtaining the output through the AI model, and this output is the inference result. The inference result can indicate the configuration parameters used (executed) by the execution object and / or the operations executed by the execution object. In the inference result application phase, the inference result is published. For example, the inference result can be uniformly planned by the execution entity. For example, the execution entity can send the inference result to one or more execution objects (such as network devices or terminal devices, etc.) for execution. Another example is that the execution entity can also feedback the performance of the model to the data source to facilitate subsequent implementation of model update training.

[0141] It can be understood that network elements with artificial intelligence capabilities can be included in the communication system. The above-mentioned phases related to AI model design can be executed by one or more network elements with artificial intelligence capabilities. In a possible design, AI capabilities (such as AI modules or AI entities) can be configured in existing network elements in the communication system to implement AI-related operations, such as training and / or inference of AI models. For example, the existing network element can be a network device or a terminal device, etc. Or in another possible design, independent network elements can also be introduced in the communication system to execute AI-related operations, such as training AI models. The independent network element can be called an AI network element or an AI node, etc., and the embodiments of the present application do not limit this name. Exemplarily, the AI network element can be directly connected to the network device in the communication system, or can be indirectly connected to the network device through a third-party network element. Among them, the third-party network element can be a core network element such as an authentication management function (AMF) network element, a user plane function (UPF) network element, an operation administration and maintenance (OAM), a cloud server or other network elements, without limitation. Exemplarily, the independent network element can be deployed on one or more of the network device side, the terminal device side, or the core network side. Optionally, it can be deployed on a cloud server. Exemplarily, such as Figure 4An AI network element 140 is introduced into the communication system shown.

[0142] The training processes of different models can be deployed in different devices or nodes, or can also be deployed in the same device or node. The inference processes of different models can be deployed in different devices or nodes, or can also be deployed in the same device or node. Taking the terminal device to complete the model training phase as an example, after the terminal device trains the supporting encoder and decoder, it can send the model parameters of the decoder among them to the network device. Taking the network device to complete the model training phase as an example, after the network device trains the supporting encoder and decoder, it can indicate the model parameters of the encoder among them to the terminal device. Taking an independent AI network element to complete the model training phase as an example, after the AI network element trains the supporting encoder and decoder, it can send the model parameters of the encoder among them to the terminal device and send the model parameters of the decoder among them to the network device. Furthermore, the model inference phase corresponding to the encoder is carried out in the terminal device, and the model inference phase corresponding to the decoder is carried out in the network device.

[0143] Among them, the model parameters can include one or more of the following: structural parameters of the model (such as the number of layers of the model, and / or weights, etc.), input parameters of the model (such as input dimension, number of input ports), or output parameters of the model (such as output dimension, number of output ports). It can be understood that the input dimension can refer to the size of an input data. For example, when the input data is a sequence, the input dimension corresponding to the sequence can indicate the length of the sequence. The number of input ports can refer to the number of input data. Similarly, the output dimension can refer to the size of an output data. For example, when the output data is a sequence, the output dimension corresponding to the sequence can indicate the length of the sequence. The number of output ports can refer to the number of output data.

[0144] 9. Model training: The process of training the model parameters by selecting an appropriate loss function and using an optimization algorithm so that the value of the loss function is less than a threshold, or so that the value of the loss function meets the target requirements.

[0145] 10. Model application: Using the trained model to solve practical problems.

[0146] Currently, for the training of the AI model on the UE side, the UE often triggers the relevant data collection by itself. At the same time, since it is a unilateral model, if there are different models on the UE side that meet different requirements, it is necessary to obtain the association relationship between a set of data sets and the AI model through the input and output of the AI model. Or obtain the association relationship between a set of data sets and the AI model through the corresponding relationship between the input and the output. For example, in AI-based sparse beam management, the input is often determined by the RSRP obtained by scanning a subset of all beams, and the output predicted by the model is the information of all beams, which can be the RSRP of all beams predicted or the probability that each beam in all beams becomes the optimal beam. Or identify the corresponding relationship between each input-output and the AI model through the quasi-colocation (QCL) relationship corresponding to the input and output. Or, obtain the corresponding relationship between the input-output and the AI model through more direct information, such as the beam shape, beamwidth, etc. of the network-side beams in beam management.

[0147] That is, for the UE side to train the AI model, it is necessary to obtain the relevant configuration information of the AI model input and output to associate different AI models with different configurations. However, this will expose the private information of the network side. For example, taking the training of beam management as an example, the relevant information of beam management involves how the network side configures the transmission beam for the input of different AI models and the arrangement of all beams, exposing the private information of the network side.

[0148] In view of this, the present application proposes a communication method that can avoid the leakage of the private information of network devices by grouping the training data and sending the training data required by the AI model.

[0149] It should be noted that in the embodiments of the present application, (pre)-configuration can be understood as configuration or pre-configuration. Among them, configuration means that it is configured by a network device, such as a network device configuring resource pool information. Pre-configuration means that it is predefined by a communication system (such as a communication system predefined resource pool information), or predefined by a communication protocol (such as a communication protocol predefined resource pool information), or pre-configured when a terminal device leaves the factory (such as a terminal device pre-configuring resource pool information when it leaves the factory), or configured by a high-layer signaling of the terminal device (such as a radio resource control (RRC) signaling).

[0150] It should be understood that in this application, an indication includes a direct indication (also referred to as an explicit indication) and an implicit indication. Among them, directly indicating information A means including the information A; implicitly indicating information A means indicating information A through the correspondence relationship between information A and information B and directly indicating information B. Among them, the correspondence relationship between information A and information B can be predefined, pre-stored, pre-burned, or pre-configured.

[0151] It should be understood that in this application, information C is used for the determination of information D, which includes both the case where information D is determined only based on information C and the case where it is determined based on information C and other information. In addition, when information C is used for the determination of information D, there may also be an indirect determination case, for example, the case where information D is determined based on information E and information E is determined based on information C.

[0152] In addition, for "device A sends information A to device B" in the embodiments of this application, it can be understood that the destination of the information A or the intermediate device in the transmission path between the destination is device B, which may include directly or indirectly sending information to device B. "Device B receives information A from device A" can be understood that the source of the information A or the intermediate device in the transmission path between the source is device A, which may include directly or indirectly receiving information from device A. Necessary processing may be performed on the information between the source and the destination of the information transmission, such as format change, etc., but the destination can understand the valid information from the source. Similar expressions in this application can be understood similarly and will not be elaborated here. Devices and apparatuses in this application can be understood interchangeably.

[0153] It should be understood that the communication method of this application can be applicable between network devices and between terminal devices, and can also be applicable between network devices and terminal devices. The following takes network devices (such as the first network device, the second network device) and terminal devices (such as the first training device, the second training device, and the training device can be a UE for example) as examples of the execution entities for illustration.

[0154] As Figure 7 shown, the method includes the following steps:

[0155] S710, the first network device obtains first data.

[0156] The first data belongs to at least one data set, and the at least one data set is used for the training of at least one AI model. The first data is used for training the first AI model, and the first AI model belongs to the above at least one AI model.

[0157] Each dataset in the at least one dataset corresponds to an AI model. In a possible implementation, the types of AI models can be divided according to the functions of the AI models. For example, the AI model for beam management training is one type of AI model, and the AI model for positioning training is another type of AI model. In other words, the at least one dataset corresponds to the functions of at least one type of AI model. Exemplarily, dataset A corresponds to the AI model for beam management training, and dataset B corresponds to the AI model for positioning training. The above "corresponds to" can be understood as "for". For example, the data included in dataset A is for beam management training data, or it can be said that the data included in dataset A can be used as the input of the AI model for beam management training.

[0158] Among them, the at least one dataset can also be at least one data group. In the embodiments of the present application, the form of multiple data is not limited. The dataset or the data group can also be referred to as multiple data.

[0159] The first data is the data in the at least one dataset. Further, the first data is the data in the first dataset, and the first dataset belongs to the at least one dataset. For example, there are 3 datasets, which correspond to three AI models respectively. Dataset A corresponds to AI model A, dataset B corresponds to AI model B, and dataset C corresponds to AI model C. The first data is the data in dataset C.

[0160] The first data can be part of the data in the first dataset. For example, if the first dataset includes 4 data, the first data can be 1 of them, or 2 of them, or 3 of them.

[0161] The first data can also be all the data in the first dataset. For example, if the first dataset includes 4 data, the first data includes these 4 data.

[0162] The above corresponding relationships between different datasets and different AI models can be preset or configured. The configuration method will be described below.

[0163] In a possible way, the training device reports feature information to the first network device. The feature information can be the information of the training device itself or the feature information of the AI model of the training device.

[0164] Specifically, the information of the training device itself can be the identifier of the training device, the brand of the training device, the index of the training device, or the computing power information of the training device. Taking beam management as an example, the maximum number of beams that can be scanned within a reference signal configuration period is the computing power of the training device. The identifier of the training device, the brand of the training device, and the index of the training device are only examples, and other ways that can uniquely identify the training device are also applicable to this application and should be within the protection scope of this application.

[0165] The feature information of the AI model can be at least one of the function of the AI model, the identifier of the AI model, or the training requirements of the AI model. Among them, the training requirements of the AI model can be the type of the required dataset, the size of the required dataset, the features of the required dataset, and so on. Among them, the type of the required dataset can be the use of the dataset. For example, one type of dataset is used for training beam management, and another type of dataset is used for training positioning. The size of the required dataset can be understood as the amount of data contained in the required dataset. For example, a dataset contains 100,000 data, and the size of this dataset is 100,000 (W). The features of the required dataset can be the commonalities of the data contained in the dataset.

[0166] The first network device can allocate data according to the above-mentioned feature information. That is, the first network device determines the first data from at least one dataset according to the first information. For example, the first network device allocates the data in the first dataset to AI model A and the data in the second dataset to AI model B. Further, the first network device can also determine the size of the allocated data for different training devices according to the above-mentioned feature information. For example, the first network device receives N first information from N training devices, and the first network device determines the size of the first data according to the number of the first information corresponding to the first AI model and the total amount of data corresponding to the first AI model. For example, the total size of the dataset supporting the training of one AI model (that is, the total amount of data corresponding to the first AI model) may be 100,000 data, and the number of training devices with the same training characteristics is N (also the number of the first information corresponding to the first AI model), then the size of the data transmitted to each training device through the data channel is 100,000 / N.

[0167] Optionally, the above step of allocating data can also be performed by the second network device, such as the core network allocating data. In this case, the first network device reports the aforementioned feature information collected to the core network (that is, the first network device sends the fourth information to the second network device), and the core network allocates data for different training devices. The specific data allocation method can refer to the allocation method of the first network device above and will not be elaborated.

[0168] In a possible implementation, when multiple training devices belong to different cells, the core network can also allocate data to different cells. The specific allocation method is similar to the aforementioned allocation method. For example, after receiving the relevant information reported by the first network device, the core network integrates the different requirements of different cells and simultaneously demarcates the corresponding resource allocation situation. For instance, assuming that the size of the dataset required for training each type of AI model is 100,000, and there are more training devices in cell 1 that need to collect datasets related to beam management, accounting for approximately 80% of all the training devices that need to train models related to beam management, then the core network notifies the first network device A to transmit 80,000 subsets of the dataset for beam management. The dataset allocation for other cells is similar. For positioning training, relevant data can also be allocated based on the reported information.

[0169] It should be noted that the core network only undertakes the task of allocation at this time and does not perform the transfer of the dataset. For example, the core network only needs to notify the first network device of how much dataset needs to be transferred for a certain training feature, and the function of dataset transfer itself is completed by the first network device. By way of example, the second network device sends the fifth information to the first network device, and the fifth information indicates the size of the first data, and the size of the first data is determined according to the total amount of data corresponding to the first AI model and N. The first network device can obtain the first data based on this fifth information.

[0170] In another possible implementation, the core network can serve as a communication medium for over-the-top (OTT) services. In this way, it can be separated from the air interface data transfer itself. The core network can directly obtain the feature information of the training devices for training different AI models through the OTT server, and directly perform data allocation and integration based on the obtained feature information, without the need for the first network device to report the feature information. This further reduces the communication process, lowers the device power consumption, and is beneficial to reducing the communication delay.

[0171] S720, the first network device sends the first data to the first training device. Correspondingly, the first training device receives the first data.

[0172] By way of example, the first network device sends the first data to the first training device through the data channel.

[0173] Optionally, there may be multiple training devices. The first network device may send data to the multiple training devices through a data channel. Among them, the first network device sends first data to the first training device, and the first network device sends second data to the second training device. The first data and the second data are different. For example, the first data is a part of the first data set, and the second data is another part of the first data set. For example, the first data set includes four data, namely data A, data B, data C, and data D. The first network device sends data A and data B to the first training device, and the first network device sends data C and data D to the second training device. The characteristics of the AI models corresponding to the first training device and the second training device are the same, for example, both are used for positioning training.

[0174] Specifically, the first training device and the second training device are classified together because they have the same AI model training requirements. The first network device then sends different data sets for training the same model or requirement to them through the data channel. At this time, different subsets of the data sets with the same characteristics are transmitted to them. For example, for the training of the beam management AI model, the training device needs to obtain the input and output of the model. Then the composition method of the data set may be the received reference signal power (reference signal receive power, RSRP) of the input and the RSRP or the identity (identity, ID) of the optimal beam of the output. Based on this, the single data set received by the first training device can be [RSRP_1, ID_1], and the data set received by the second training device can be [RSRP_2, ID2]. At the same time, it should be noted that at this time, the data sets received by the first training device and the second training device can both be a subset of the data set that supports the training of the same AI model. Of course, the data of the first training device and the second training device can also be the same, and this application does not limit this.

[0175] In addition, the characteristics of the AI models of the first training device and the second training device may be different. For example, the first training device corresponds to AI model A and is used for positioning training. The second training device corresponds to AI model B and is used for beam management training. In this case, the first network device sends first data to the first training device, and the first network device sends second data to the second training device. The first data is the data in the first data set, and the second data is the data in the second data set. That is to say, the inputs of the first training device and the second training device belong to different data sets.

[0176] Optionally, the method may further include the following steps:

[0177] S730, the first training device sends second information to the first network device. Correspondingly, the first network device receives the second information.

[0178] The second information indicates that the data received by the first training device is sufficient for the training of the first AI model, or the second information indicates that the data received by the first training device is insufficient for the training of the first AI model.

[0179] That is, the first network device can download the data corresponding to the AI model through the data channel, and the training device determines and feeds back whether the required amount of data has been received, and can also synchronize the progress of receiving the data. This method is applicable to the case where the first network device does not allocate the data volume to the training device. When the first network device determines the data volume for different training devices respectively, whether the data received by the first training device is sufficient for the training of the first AI model can be determined by the first network device.

[0180] When the first network device determines that the data transmission is completed, or the second information received by the first network device indicates that the data received by the first training device is sufficient for the training of the first AI model, the first network device can also send the third information to the first training device. Correspondingly, the first training device receives the third information, and the third information indicates the end of the first data transmission. Or it can be said that the third information is used to indicate the completion of the data transmission this time.

[0181] It should be understood that the completion of the data transmission of a certain training device does not affect the data transmission of other training devices. For example, when the first training device receives the third information and the data transmission of the first training device is completed, the data transmission of other training devices such as the second training device or the third training device can continue until the data transmission is completed.

[0182] At the same time, corresponding indication information can be configured in the transmitted data to indicate the use of this type of data. For example, it indicates which one or which data in a set of data is used to obtain the input of the AI model, and which one or which data is used to obtain the output of the AI model.

[0183] S740, the first training device trains the first AI model based on the first data.

[0184] Exemplarily, the training device can perform integration and training on the received data based on its own mechanism of the training device. The training device can train the received data locally. It can also be trained non-locally. For example, all the data can be uploaded to the OTT server of the training device, and the OTT server performs data integration and trains the AI model. After the model training is completed, the corresponding AI model can be sent or configured to each training device. Specifically, the method for the training device to train the AI model can refer to the prior art, and will not be elaborated in this application.

[0185] In this method, the network device transmits data to the training device through the air interface, avoiding the leakage of the private information of the network device. In addition, the network device classifies the training data to correspond to different training requirements, and sends the corresponding training data to different training models, further reducing the complexity of the training device to obtain the required data and saving the device power consumption.

[0186] To facilitate the understanding of the communication method of this application, two exemplary implementation processes are given below.

[0187] Implementation 1: Taking the first network device as the gNB as an example, taking UE1 as an example of the first training device, UE2 as an example of the second training device, and UE3 as an example of the third training device, as Figure 8 shown, this implementation includes the following steps:

[0188] S810, UE1 sends Feature 1 to the gNB. Correspondingly, the gNB receives this Feature 1.

[0189] S820, UE2 sends Feature 2 to the gNB. Correspondingly, the gNB receives this Feature 2.

[0190] S830, UE3 sends Feature 3 to the gNB. Correspondingly, the gNB receives this Feature 3.

[0191] The above Feature 1, Feature 2, and Feature 3 can refer to the description of the feature information (or the first information) in S710, which will not be elaborated here.

[0192] S840, the gNB groups different UEs according to the feature information.

[0193] Exemplarily, the gNB divides the three UEs into two groups according to the usage of the AI model. For example, UE1 and UE2 are in the same group, and the AI models corresponding to UE1 and UE2 are both used for positioning training. UE3 belongs to another group, and the AI model corresponding to UE3 is used for beam management training.

[0194] S850, the gNB groups the data according to the feature information.

[0195] For example, the gNB classifies the data according to the usage of the AI model. For example, dataset A is used for positioning training, and dataset B is used for beam management training. The specific data classification method can refer to the description in S710, which will not be elaborated here.

[0196] S860, the gNB sends data A to UE1. Correspondingly, UE1 receives this data A.

[0197] S870, the gNB sends data B to UE2. Correspondingly, UE1 receives this data B.

[0198] Among them, data A and data B belong to the same data set.

[0199] S880, the gNB sends data C to UE3. Correspondingly, UE1 receives the data C.

[0200] The data set to which data C belongs is different from the data sets to which data A and data B belong.

[0201] S890, the gNB determines whether the data transmission is completed.

[0202] S8100, the gNB sends a data transmission completion indication to UE1. Correspondingly, UE1 receives the data transmission completion indication.

[0203] S8110, the gNB sends a data transmission completion indication to UE2. Correspondingly, UE2 receives the data transmission completion indication.

[0204] This data transmission completion indication is an example of the third information.

[0205] The gNB stops the transmission of data A and data B, but the transmission of data C is not affected. For example, data C can continue to be transmitted until the transmission is completed and then the gNB sends a data transmission completion indication to UE3.

[0206] S8120, the UE trains an AI model based on the received data.

[0207] In this implementation, S810 to S840, S8100, and S8110 are all optional steps.

[0208] In this implementation, the network device classifies the training device, classifies the data set, and transmits the corresponding data to the training device through the air interface, avoiding the leakage of the private information of the network device.

[0209] Implementation 2: Taking the first network device as gNB1 as an example, the second network device as the core network as an example, the third network device as gNB2 as an example, UE1 as an example of the first training device, UE2 as an example of the second training device, UE3 as an example of the third training device, and UE4 as an example of the fourth training device. UE1 and UE2 belong to the first cell, and the base station in the first cell is gNB1; UE3 and UE4 belong to the second cell, and the base station in the second cell is gNB2.

[0210] As Figure 9 shown, this implementation includes the following steps:

[0211] S910, UE1 sends feature 1 to gNB1. Correspondingly, gNB1 receives the feature 1.

[0212] S920, UE2 sends Feature 2 to gNB1. Correspondingly, gNB1 receives this Feature 2.

[0213] S930, UE3 sends Feature 3 to gNB2. Correspondingly, gNB2 receives this Feature 3.

[0214] S940, UE4 sends Feature 4 to gNB2. Correspondingly, gNB2 receives this Feature 4.

[0215] The above Feature 1, Feature 2, Feature 3, and Feature 4 can refer to the description of the feature information (or the first information) in S710, which will not be elaborated here.

[0216] S950, gNB1 sends cell information to the core network. Correspondingly, the core network receives this cell information.

[0217] S960, gNB2 sends cell information to the core network. Correspondingly, the core network receives this cell information.

[0218] This cell information can include the number of UEs included in the cell and the above feature information.

[0219] S970, the core network groups the UEs.

[0220] Exemplarily, the core network groups the UEs according to the usage of the AI models of the UEs. For example, UE1 and UE4 are grouped into one group, and UE2 and UE3 are grouped into one group.

[0221] S980, the core network allocates data.

[0222] Specifically, it can refer to the data allocation method in S710, which will not be elaborated here.

[0223] S990, the core network sends indication information A to gNB1. Correspondingly, gNB1 receives indication information A.

[0224] This indication information A indicates the data allocated to UE1 and UE2, such as the size of the data.

[0225] S9100, the core network sends indication information B to gNB2. Correspondingly, gNB1 receives indication information B.

[0226] This indication information B indicates the data allocated to UE3 and UE4, such as the size of the data.

[0227] This indication information A and indication information B are examples of the fifth information.

[0228] S9110, gNB1 sends data 1 to UE1. Correspondingly, UE1 receives data 1.

[0229] In S9120, gNB1 sends Data 2 to UE2. Correspondingly, UE2 receives Data 2.

[0230] In S9130, gNB2 sends Data 3 to UE3. Correspondingly, UE3 receives Data 3.

[0231] In S9140, gNB2 sends Data 4 to UE4. Correspondingly, UE4 receives Data 4.

[0232] Optionally, when the data transmission is completed, the gNB can also send indication information to the UE corresponding to the data to indicate the end of the data transmission.

[0233] In S9150, each UE trains the AI model based on the received data.

[0234] In this implementation, the core network coordinates the UEs and data in different cells, and the gNB is responsible for the air interface transmission of the data. This is applicable to scenarios with multiple training devices and multiple cells.

[0235] Each implementation described in this article can be an independent solution or can be combined according to the internal logic. All these solutions fall within the protection scope of this application.

[0236] In the above embodiments provided by this application, the methods provided by the embodiments of this application are introduced from the perspective of the interaction between various devices. To implement each function in the methods provided by the above embodiments of this application, a network device or a terminal device may include a hardware structure and / or a software module, and implement the above functions in the form of a hardware structure, a software module, or a combination of a hardware structure and a software module. Whether a certain function among the above functions is executed in the form of a hardware structure, a software module, or a combination of a hardware structure and a software module depends on the specific application and design constraints of the technical solution.

[0237] The division of modules in the embodiments of this application is illustrative, and is only a logical function division. There may be other division methods in actual implementation. In addition, in each embodiment of this application, each functional module may be integrated in a processor, may exist separately physically, or two or more modules may be integrated in one module. The above integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0238] Similar to the above concept, as Figure 10 shown, the embodiments of this application also provide a device 1000 for implementing the functions of the sending device or the receiving device in the above method. For example, the device may be a software module or a chip system. In the embodiments of this application, the chip system may be composed of chips or may include chips and other discrete devices. The device 1000 may include: a processing unit 1010 and a communication unit 1020.

[0239] In the embodiments of the present application, the communication unit may also be referred to as a transceiver unit, and may include a sending unit and / or a receiving unit, which are respectively used to execute the sending and receiving steps of the sending device or the receiving device in the above method embodiments.

[0240] Hereinafter, in conjunction with Figures 10 to 12 The communication device provided in the embodiments of the present application will be described in detail. It should be understood that the description of the device embodiments corresponds to the description of the method embodiments. Therefore, for the content not described in detail, reference may be made to the above method embodiments. For the sake of brevity, it will not be repeated here.

[0241] The communication unit may also be referred to as a transceiver, a transceiver, a transceiver device, etc. The processing unit may also be referred to as a processor, a processing board, a processing module, a processing device, etc. Optionally, the devices in the communication unit 1020 used to implement the receiving function may be regarded as the receiving unit, and the devices in the communication unit 1020 used to implement the sending function may be regarded as the sending unit, that is, the communication unit 1020 includes a receiving unit and a sending unit. The communication unit may sometimes also be referred to as a transceiver, a transceiver, or an interface circuit, etc. The receiving unit may sometimes also be referred to as a receiver, a receiver, or a receiving circuit, etc. The sending unit may sometimes also be referred to as a transmitter, a transmitter, or a transmitting circuit, etc.

[0242] When the communication device 1000 executes the functions of the network device in the process shown in the above embodiments Figure 7 :

[0243] The communication unit is used for the sending and receiving of information. For example, sending data, receiving the first information, receiving the second information, sending the third information, sending the fourth information, receiving the fifth information, etc.

[0244] The processing unit is used to obtain data.

[0245] When the communication device 1000 executes the functions of the training device in the process shown in any of the above embodiments Figure 7 :

[0246] The processing unit is used to train an AI model according to the data, etc.

[0247] The communication unit is used to send and receive information. For example, it is used to receive data, or receive the third information, etc.

[0248] The above are only examples. The processing unit 1010 and the communication unit 1020 may also execute other functions. For a more detailed description, reference may be made to Figure 3 the relevant descriptions in the shown method embodiments or other method embodiments, which will not be elaborated here.

[0249] As another possible product form, the sending device and the receiving device described in the embodiments of the present application can be implemented by a general bus architecture. For ease of description, refer to Figure 11 , Figure 11 FIG. Figure 11 is a schematic structural diagram of a communication device 1100 provided by an embodiment of the present application. The communication device 1100 includes a processor 1101 and a transceiver 1102. The communication device 1100 can be a first terminal device, or a chip or a chip system therein; or, the communication device 1100 can be a second terminal device, or a chip or a module therein; or, the communication device 1100 can be a third terminal device, or a chip or a module therein; or, the communication device 1100 can be a fourth terminal device, or a chip or a module therein; or, the communication device 1100 can be a fifth terminal device, or a chip or a module therein; or, the communication device 1100 can be a sixth terminal device, or a chip or a module therein. Figure 11 Only the main components of the communication device 1100 are shown. In addition to the processor 1101 and the transceiver 1102, the communication device 1100 may further include a memory 1103 and an input / output device (not shown in the figure).

[0250] Optionally, the processor 1101 is mainly used to process communication protocols and communication data, control the entire communication device, execute software programs, and process data of software programs. The memory 1103 is mainly used to store software programs and data. The transceiver 1102 may include a radio frequency circuit and an antenna. The radio frequency circuit is mainly used for the conversion between baseband signals and radio frequency signals and the processing of radio frequency signals. The antenna is mainly used to transmit and receive radio frequency signals in the form of electromagnetic waves. The input / output device, such as a touch screen, a display screen, a keyboard, etc., is mainly used to receive data input by the user and output data to the user.

[0251] Optionally, the processor 1101, the transceiver 1102, and the memory 1103 can be connected through a communication bus.

[0252] After the communication device is powered on, the processor 1101 can read the software program in the memory 1103, interpret and execute the instructions of the software program, and process the data of the software program. When data needs to be wirelessly transmitted, the processor 1101 performs baseband processing on the data to be transmitted, and then outputs a baseband signal to the radio frequency circuit. The radio frequency circuit performs radio frequency processing on the baseband signal and then transmits the radio frequency signal outward in the form of electromagnetic waves through the antenna. When data is sent to the communication device, the radio frequency circuit receives the radio frequency signal through the antenna, converts the radio frequency signal into a baseband signal, and outputs the baseband signal to the processor 1101. The processor 1101 converts the baseband signal into data and processes the data.

[0253] In another implementation, the radio frequency circuit and the antenna can be arranged independently of the processor performing baseband processing. For example, in a distributed scenario, the radio frequency circuit and the antenna can be arranged in a remote manner independent of the communication device.

[0254] In some embodiments, in terms of hardware implementation, those skilled in the art can conceive that the above-mentioned communication device 110 can adopt Figure 11 the form of the communication device 1100 shown.

[0255] As an example, Figure 11 the function / implementation process of the processing module 1020 in Figure 11 can be implemented by the processor 1101 in the communication device 1100 shown calling computer-executable instructions stored in the memory 1103. Figure 11 the function / implementation process of the transceiver module 1010 in Figure 11 can be implemented by the transceiver 1102 in the communication device 1100 shown.

[0256] As another possible product form, the first terminal device, the second terminal device, the third terminal device, the fourth terminal device, the fifth terminal device, or the sixth terminal device in the present application can adopt Figure 12 the composition structure shown, or include Figure 12 the components shown. Figure 12 is a schematic diagram of the composition of a communication device 1200 provided by the present application.

[0257] As Figure 12 shown, the communication device 1200 includes at least one processor 1201. Optionally, the communication device further includes a communication interface 1202.

[0258] When the program instructions involved are executed in the at least one processor 1201, the device 1200 can implement the method provided in any of the foregoing embodiments and any possible design therein. Alternatively, the processor 1201 is used to implement the method provided in any of the foregoing embodiments and any possible design therein through logic circuits or by executing code instructions.

[0259] The communication interface 1202 can be used to receive program instructions and transmit them to the processor. Alternatively, the communication interface 1202 can be used for the communication device 1200 to communicate and interact with other communication devices, such as interacting control signaling and / or service data, etc. Exemplarily, the communication interface 1202 can be used to receive signals from other devices outside the communication device 1200 and transmit them to the processor 1201 or send signals from the processor 1201 to other communication devices outside the communication device 1200.

[0260] Optionally, the communication interface 1202 may be a code and / or data read / write interface circuit, or the communication interface 1202 may be a signal transmission interface circuit between the communication processor and the transceiver, or a pin of the chip.

[0261] Optionally, the communication device 1200 may further include at least one memory 1203, which may be used to store the required program instructions and / or data. It should be noted that the memory 1203 may exist independently of the processor 1201 or may be integrated with the processor 1201. The memory 1203 may be located inside the communication device 1200 or outside the communication device 1200, without limitation.

[0262] Optionally, the communication device 1200 may further include a power supply circuit 12011, which may be used to supply power to the processor 1201. The power supply circuit 12011 may be located within the same chip as the processor 1201, or within another chip outside the chip where the processor 1201 is located.

[0263] Optionally, the communication device 1200 may further include a bus 12011, and various parts in the communication device 1200 may be interconnected through the bus 12011.

[0264] In some embodiments, in terms of hardware implementation, those skilled in the art can conceive that the Figure 11 shown communication device 110 may adopt the Figure 12 form of the shown communication device 1200.

[0265] As an example, Figure 11 the function / implementation process of the processing module 1020 in Figure 12 may be implemented by the processor 1201 in the shown communication device 1200 calling the computer execution instructions stored in the memory 1203. Figure 11 the function / implementation process of the transceiver module 1010 in Figure 12 may be implemented by the communication interface 1202 in the shown communication device 1200.

[0266] It should be noted that Figure 12 the shown structure does not constitute a specific limitation on the sending device and the receiving device. For example, in other embodiments of the present application, the sending device and the second terminal device may include more or fewer components than shown, or combine certain components, or split certain components, or have different component arrangements. The shown components may be implemented in hardware, software, or a combination of software and hardware.

[0267] When the above communication device is a chip applied to a terminal device, the terminal device chip implements the functions of the terminal device in the above method embodiments. The terminal device chip receives information from other modules (such as a radio frequency module or an antenna) in the terminal device, and the information is sent by a network device to the terminal device; or, the terminal device chip sends information to other modules (such as a radio frequency module or an antenna) in the terminal device, and the information is sent by the terminal device to the network device.

[0268] When the above communication device is a chip applied to a network device, the network device chip implements the functions of the network device in the above method embodiments. The network device chip receives information from other modules (such as a radio frequency module or an antenna) in the network device, and the information is sent by a terminal device to the network device; or, the network device chip sends information to other modules (such as a radio frequency module or an antenna) in the network device, and the information is sent by the network device to the terminal device.

[0269] It can be understood that the processor in the embodiments of the present application may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0270] In an embodiment of the present application, the processor may be a random access memory (RAM), flash memory, read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), register, hard disk, removable hard disk, CD-ROM, or any other form of storage medium well-known in the art. An exemplary storage medium is coupled to the processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium may also be a component of the processor. The processor and the storage medium may be located in an ASIC. Additionally, the ASIC may be located in a network device or a terminal device. Of course, the processor and the storage medium may also exist as discrete components in a network device or a terminal device.

[0271] Those skilled in the art should understand that the embodiments of the present application may be provided as a method, a system, or a computer program product. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, optical storage, etc.) containing computer-usable program code.

[0272] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or combinations of blocks.

[0273] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or combinations of blocks.

[0274] Obviously, those skilled in the art can make various changes and modifications to this application without departing from the scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalent technologies, this application is also intended to cover these modifications and variations.

[0275] As described above, it is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application. Therefore, the protection scope of this application shall be subject to the protection scope of the said claims.

Claims

1. A communication method, characterized in that, Applied to a first training device, including: Receiving first data from a first network device, the first data belonging to at least one data set, and the at least one data set being used for training at least one artificial intelligence (AI) model; Training a first AI model based on the first data, the first AI model belonging to the at least one AI model.

2. The method according to claim 1, characterized in that, The method further includes: Sending first information to the first network device, the first information indicating the characteristic information of the first training device, and / or the first information indicating the characteristic information of the first AI model.

3. The method according to claim 2, wherein The characteristic information of the first training device includes the identification information and / or computing power information of the first training device, and the characteristic information of the first AI model includes at least one of the use of the first AI model, the identification information of the first AI model, the type of data required by the first AI model, or the size of the data required by the first AI model.

4. The method according to any one of claims 1 to 3, characterized in that, The method further includes: Sending second information to the first network device, the second information indicating that the data received by the first training device is sufficient for training the first AI model, or the second information indicating that the data received by the first training device is insufficient for training the first AI model.

5. The method according to claim 4, wherein The second information further indicates the reception progress of the first data.

6. The method according to any one of claims 1 to 5, characterized in that The method further includes: Receiving third information, the third information indicating the end of the transmission of the first data.

7. A communication method, applied to a first network device, characterized in that, Including: Obtaining first data, the first data belonging to at least one data set, the at least one data set being used for training at least one AI model, the first data being used for training a first AI model, and the first AI model belonging to the at least one AI model; Sending the first data to the first training device.

8. The method according to claim 7, wherein The method further includes: Receiving first information from the first training device, the first information indicating the characteristic information of the first training device, or the first information indicating the characteristic information of the first AI model.

9. The method according to claim 8, wherein The characteristic information of the first training device includes the identification information and / or computing power information of the first training device, and the characteristic information of the first AI model includes at least one of the use of the first AI model, the identification information of the first AI model, the type of data required by the first AI model, or the size of the data required by the first AI model.

10. The method according to claim 9, characterized in that, The obtaining of the first data includes: Determining the first data from the at least one data set according to the first information.

11. The method according to claim 9 or 10, characterized in that, The method further includes: Receiving N first information from N training devices, the N first information respectively indicating the characteristic information of the N training devices, or the N first information indicating the characteristic information of M AI models, The determining of the first data includes: Determining the size of the first data according to the number of the first information corresponding to the first AI model and the total amount of data corresponding to the first AI model.

12. The method according to any one of claims 7 to 10, characterized in that, The method further includes: Receiving second information from the first training device, the second information indicating that the first training device has received the amount of data required for training the first AI model, or has not received the amount of data required for training the first AI model.

13. The method according to claim 12, wherein The second information further indicates the reception progress of the first data.

14. The method according to any one of claims 7 to 13, characterized in that, The method further includes: Sending third information to the first training device, where the third information indicates the end of the first data transmission.

15. The method according to claim 9, wherein The method further includes: Sending fourth information to a second network device, where the fourth information indicates the feature information of the N training devices, or the feature information of the M first AI models.

16. The method according to claim 15, wherein The obtaining of the first data includes: Receiving fifth information from the second network device, where the fifth information indicates the size of the first data, and the size of the first data is determined according to the total amount of data corresponding to the first AI model and the N; Obtaining the first data according to the fifth information.

17. A communication method, applied to a second network device, characterized in that, Includes: Receiving fourth information, where the fourth information indicates the feature information of N training devices, or the feature information of M first AI models, and the first AI model belongs to at least one type of AI model; Determining first data according to the fourth information and at least one data set, where the at least one data set is used for training at least one type of AI model, and the first data is used for training the first AI model.

18. The method according to claim 17, wherein Determining first data according to the fourth information and at least one data set includes: Determining the size of the first data according to the total amount of data corresponding to the first AI model and the N, and the data corresponding to the first AI model belongs to the at least one data set.

19. The method according to claim 17 or 18, characterized in that, The method further includes: Sending fifth information, where the fifth information indicates the size of the first data.

20. A communication device, characterized in that, Includes a module or unit for performing the method according to any one of claims 1 to 6.

21. A communication device, characterized in that, Includes a module or unit for performing the method according to any one of claims 7 to 16, or the method according to any one of claims 17 to 19.

22. A communication system, characterized in that, Includes a communication device as claimed in claims 20 and 21.

23. A computer-readable storage medium, characterized in that, A computer program or instruction is stored on the computer-readable storage medium. When the computer program or instruction runs on the communication device, the communication device is caused to perform the method according to any one of claims 1 to 6, or the method according to any one of claims 7 to 16, or the method according to any one of claims 17 to 19.

24. A computer program product, characterized in that, The computer program product includes a computer program or instruction for performing the method according to any one of claims 1 to 6, or the method according to any one of claims 7 to 16, or the method according to any one of claims 17 to 19.

25. A chip, characterized in that, The chip includes a processor and a communication interface. The processor reads an instruction stored in a memory through the communication interface and executes the method according to any one of claims 1 to 6, or the method according to any one of claims 7 to 16, or the method according to any one of claims 17 to 19.

Images