Communication method, apparatus and system

Abstract

The present application provides communication methods, an apparatus and a system, the methods being applicable to communication scenarios such as an AI model training scenario. In a method, a network device transmits data to a training apparatus by means of an air interface, avoiding leakage of private information of the network device. In addition, the network device classifies training data so as to correspond to different training requirements, and issues respective training data to different training models, further reducing the complexity of the training apparatus acquiring required data, and saving device power consumption.

Description

Communication method, device and system

[0001] This application claims priority to the Chinese patent application with application number 202410126783.1 filed with the State Intellectual Property Office of China on January 29, 2024, and priority to the Chinese patent application with the invention name “Communication Method, Device and System”, all contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of communications, and in particular to a communication method, device, and system. Background Art

[0003] Machine learning is an important technical approach to achieving artificial intelligence (AI). Training AI models on user equipment (UE) often involves the UE itself triggering data collection. To train AI models, the UE needs to obtain configuration information related to the AI ​​model's input and output to associate different AI models with different configurations. However, this information, because it involves how the network configures input information for different AI models, has the disadvantage of exposing private information on the network side. Summary of the Invention

[0004] The present application provides a communication method, device, and system that can prevent the leakage of private information of network devices.

[0005] In a first aspect, a communication method is provided. The method may be executed by a first training device, or may be executed by a chip or circuit used in the first training device, which is not limited in this application. For ease of description, the following description is based on the first training device as an example.

[0006] The method includes: 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 AI model; training a first AI model based on the first data, the first AI model belonging to the at least one AI model.

[0007] In this method, the network device transmits data to the training device through the air interface, thereby avoiding the leakage of private information of the network device.

[0008] In some implementations, the first data is input data of a first training device, the second data is input data of a 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.

[0009] In this method, different training devices correspond to different data, and multiple training devices can synchronously receive the data required by the same AI model, improving data reception efficiency.

[0010] In some implementations, first information is sent to a first network device, where the first information indicates characteristic information of the first training device, and / or the first information indicates characteristic information of the first AI model.

[0011] 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.

[0012] In some 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.

[0013] 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.

[0014] 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.

[0015] In some implementations, the second information further indicates a progress of receiving the first data.

[0016] In some implementations, third information is received, the third information indicating an end of the first data transmission.

[0017] 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.

[0018] 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.

[0019] The method includes: acquiring 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;

[0020] First data is sent to a first training device.

[0021] In some implementations, second data is sent 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 functions.

[0022] In some implementations, first information is received from the first training device, where the first information indicates characteristic information of the first training device, or the first information indicates characteristic information of the first AI model.

[0023] In some 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.

[0024] In some implementations, the first data is determined from the at least one data set based on the first information.

[0025] In some implementations, N first information are received from N training devices, where the N first information respectively indicate characteristic information of the N training devices, or the N first information indicate characteristic information of M AI models. Determining the first data includes: determining the size of the first data based on the number of first information corresponding to the first AI model and the total amount of data corresponding to the first AI model.

[0026] 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 to train the first AI model, or has not received the amount of data required to train the first AI model.

[0027] In some implementations, the second information further indicates a progress of receiving the first data.

[0028] In some implementations, third information is sent to the first training device, where the third information indicates that the first data transmission is finished.

[0029] In some implementations, fourth information is sent to the second network device, where the fourth information indicates characteristic information of the N training devices, or characteristic information of the M first AI models.

[0030] In this manner, the first network device reports the characteristic information to the second network device, so that the second network device can perform data distribution.

[0031] In some implementations, fifth information is received 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 based on the total amount of data corresponding to the first AI model and N; and the first data is obtained based on the fifth information.

[0032] In a third aspect, a communication method is provided. The method may be executed by a second network device, or may be executed by a chip or circuit for the second 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 second network device.

[0033] The method includes: receiving fourth information, the fourth information indicating characteristic information of N training devices, or characteristic information of M first AI models, the first AI model belonging to at least one AI model; determining first data based on the fourth information and at least one data set, the at least one data set being used for training at least one AI model, and the first data being used for training the first AI model.

[0034] In some implementations, determining the first data based on the fourth information and at least one data set includes: determining the size of the first data based on the total amount of data corresponding to the first AI model and N, and the data corresponding to the first AI model belongs to the at least one data set.

[0035] In some implementations, fifth information is sent, where the fifth information indicates the size of the first data.

[0036] In a fourth aspect, a communication device is provided, comprising a transceiver module and a processing module. The transceiver module is used to receive 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 to train at least one artificial intelligence (AI) model; the processing module is used to train a first AI model based on the first data, where the first AI model belongs to the at least one AI model.

[0037] In some implementations, the first data is input data of a first training device, the second data is input data of a 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.

[0038] In some implementations, the transceiver module is used to send first information to the first network device, where the first information indicates characteristic information of the first training device and / or the first information indicates characteristic information of the first AI model.

[0039] In some 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.

[0040] 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 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.

[0041] In some implementations, the second information further indicates a progress of receiving the first data.

[0042] In some implementations, the transceiver module is configured to receive third information, where the third information indicates that the first data transmission is completed.

[0043] In a fifth aspect, a communication device is provided, comprising 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, and the at least one data set is used to train 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 a first training device.

[0044] 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.

[0045] In some implementations, the transceiver module is used to receive first information from the first training device, where the first information indicates characteristic information of the first training device, or the first information indicates characteristic information of the first AI model.

[0046] In some 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.

[0047] In some implementations, the processing module is configured to determine the first data from the at least one data set based on the first information.

[0048] In some implementations, the processing module is used to receive N first information from N training devices, where the N first information respectively indicate characteristic information of the N training devices, or the N first information indicate characteristic information of M AI models. The processing module is used to determine the size of the first data based on the number of first information corresponding to the first AI model and the total amount of data corresponding to the first AI model.

[0049] In some implementations, the transceiver module is used 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 to train the first AI model, or has not received the amount of data required to train the first AI model.

[0050] In some implementations, the second information further indicates a progress of receiving the first data.

[0051] In some implementations, the transceiver module is configured to send third information to the first training device, where the third information indicates that the first data transmission is complete.

[0052] In some implementations, the transceiver module is used to send fourth information to the second network device, where the fourth information indicates characteristic information of the N training devices, or characteristic information of the M first AI models.

[0053] In some implementations, the transceiver module is used 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 based on the total amount of data corresponding to the first AI model and N; the processing module is used to obtain the first data based on the fifth information.

[0054] In a sixth aspect, a communication device is provided, comprising a transceiver module and a processing module, the transceiver module being used to receive fourth information, the fourth information indicating characteristic information of N training devices, or characteristic information of M first AI models, the first AI model belonging to at least one AI model; the processing module being used to determine first data based on the fourth information and at least one data set, the at least one data set being used for training at least one AI model, and the first data being used for training the first AI model.

[0055] In certain implementations, the processing module is configured to determine a size of the first data based on a total amount of data corresponding to the first AI model and N, where the data corresponding to the first AI model belongs to the at least one data set.

[0056] In some implementations, the transceiver module is used to send fifth information, where the fifth information indicates the size of the first data.

[0057] It should be understood that the fourth, fifth and sixth aspects are implementation methods on the device side corresponding to the first, second and third aspects. The explanations, supplements and descriptions of the beneficial effects of the first, second and third aspects are also applicable to the fourth, fifth and sixth aspects and will not be repeated here.

[0058] In the seventh aspect, the present application provides a communication device, including an interface circuit and a processor, wherein the interface circuit is used to implement the function of the transceiver module in the fourth aspect, and the processor is used to implement the function of the processing module in the third aspect.

[0059] In an eighth aspect, the present application provides a communication device, comprising an interface circuit and a processor, wherein the interface circuit is used to implement the function of the transceiver module in the fifth aspect, and the processor is used to implement the function of the processing module in the fourth aspect.

[0060] In the ninth aspect, the present application provides a communication device, including an interface circuit and a processor, wherein the interface circuit is used to implement the function of the transceiver module in the sixth aspect, and the processor is used to implement the function of the processing module in the fourth aspect.

[0061] In a tenth aspect, the present application provides a computer-readable medium storing a program code for execution by a training device, the program code comprising instructions for executing the method of the first aspect, or any possible manner of the first aspect, or all possible manners of the first aspect.

[0062] In the eleventh aspect, an embodiment of the present application provides a computer-readable medium storing a program code for execution by a network device, the program code including 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.

[0063] In the twelfth aspect, a computer program product storing computer-readable instructions is provided, which, when the computer-readable instructions are executed on a computer, enables the computer to execute the method of the first aspect, or any possible method of the first aspect, or all possible methods of the first aspect.

[0064] In the thirteenth aspect, a computer program product storing computer-readable instructions is provided, which, when the computer-readable instructions are run on a computer, enables the computer to execute the method of the above-mentioned second aspect, or the third aspect, or any possible method in the second aspect, or any possible method in the third aspect, or all possible methods in the second aspect, or all possible methods in the third aspect.

[0065] In the fourteenth aspect, a communication system is provided, which includes a method for 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 a device with various possible designed functions.

[0066] In the fifteenth aspect, a processor is provided, which is coupled to a memory and is used to execute the method of the above-mentioned first aspect, or any possible method of the first aspect, or all possible methods of the first aspect.

[0067] In the sixteenth aspect, a processor is provided for coupling with a memory, 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.

[0068] In a seventeenth aspect, a chip system is provided, comprising a processor and a memory configured to execute computer programs or instructions stored in the memory, so that the chip system implements the method of any of the aforementioned first, second, or third aspects, as well as any possible implementation of any of the aspects. The chip system may be composed of a chip alone, or may include a chip and other discrete components.

[0069] In the 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 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 first network device sends the first data to a first training device; the first training device trains a first AI model based on the first data, and the first AI model belongs to the at least one AI model.

[0070] In the nineteenth aspect, a communication method is provided, including: a second network device receives fourth information from a first network device, the fourth information indicating characteristic information of N training devices, or characteristic information of M first AI models, and the first AI model belongs to at least one AI model; the second network device determines first data based on the fourth information and at least one data set, the at least one data set is used for training at least one AI model, and the first data is used to train the first AI model; the 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 at least one AI model, the first data is used to train the first AI model, and the first AI model belongs to the at least one AI model; the first network device sends first data to the 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. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] FIG1 is a schematic diagram of a possible application framework in a communication system;

[0072] FIG2 is a schematic diagram of another possible application framework in a communication system;

[0073] FIG3 is a schematic diagram of a communication system applicable to an embodiment of the present application;

[0074] FIG4 is a schematic diagram of another communication system applicable to an embodiment of the present application;

[0075] FIG5 is a schematic block diagram of an autoencoder;

[0076] FIG6 is a schematic diagram of an AI application framework;

[0077] FIG7 is a schematic diagram of a communication method provided in an embodiment of the present application;

[0078] FIG8 is a schematic diagram of a communication process provided in an embodiment of the present application;

[0079] FIG9 is a schematic diagram of another communication process provided in an embodiment of the present application;

[0080] FIG10 is a schematic block diagram of a communication device;

[0081] FIG11 is a schematic block diagram of yet another communication device;

[0082] FIG12 is a schematic block diagram of yet another communication device. DETAILED DESCRIPTION

[0083] The technical solution in this application will be described below with reference to the accompanying drawings.

[0084] The technical solutions provided in this application can be applied to various communication systems, such as: fifth generation (5G) or new radio (NR) systems, long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, wireless local area networks (WLAN) systems, satellite communication systems, future communication systems, or integrated systems of multiple systems. The technical solutions provided in this application can also be applied to device to device (D2D) communication, vehicle-to-everything (V2X) communication, machine to machine (M2M) communication, machine type communication (MTC), and Internet of Things (IoT) communication systems or other communication systems.

[0085] 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 may include information, signaling, or data, etc. The network element can also be replaced by an entity, a network entity, a device, a communication device, a communication module, a node, a communication node, etc. The present disclosure uses the network element as an example for description. For example, the communication system may 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 is understandable that the terminal device in the present disclosure can be replaced by the first network element, and the network device can be replaced by the second network element, and the two perform the corresponding communication methods in the present disclosure.

[0086] In an embodiment of the present application, the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device.

[0087] The terminal device may be a device that provides voice / data, such as a handheld device or vehicle-mounted device with a wireless connection function. At present, some examples of terminals are: mobile phones, tablet computers, laptop computers, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices or other processing devices connected to wireless modems, wearable devices, terminal devices in 5G networks or future evolved public land mobile communication networks (PLMNs). The terminal equipment in the network (PLMN), etc., is not limited to this in the embodiments of the present application.

[0088] As an example and not a limitation, in the embodiment of the present application, the terminal device may also be a wearable device. Wearable devices may also be called wearable smart devices, which are a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing, and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are fully functional, large in size, and can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0089] In the embodiments of the present application, the device for realizing the function of the terminal device can be a terminal device, or a device capable of supporting the terminal device to realize the function, such as a chip system, which can be installed in the terminal device or used in combination with the terminal device. In the embodiments of the present application, the chip system can be composed of a chip, or it can include a chip and other discrete devices. In the embodiments of the present application, only the terminal device is used as an example for description, and the embodiments of the present application are not limited to the solutions of the embodiments of the present application.

[0090] The network device in the embodiments of the present application may be a device for communicating with a terminal device, and may also be referred to as an access network device or a radio access network device. For example, the network device may be a base station. The network device in the embodiments of the present application may refer to a radio access network (RAN) node (or device) that connects a terminal device to a wireless network. A base station may broadly cover various names as follows, or replace the following names, such as: NodeB, evolved NodeB (eNB), next generation NodeB (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master station, secondary station, multi-standard radio (motor slide retainer, 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 may be a macro base station, a micro base station, a relay node, a donor node, or the like, or a combination thereof. The base station may also refer to a communication module, modem or chip used to be set in the aforementioned equipment or device. The base station may also be a mobile switching center and a device that performs the base station function in D2D, V2X, and M2M communications, a network side device in a future communication network, a device that performs the base station function in a future communication system, etc. The base station can support networks with the same or different access technologies. Optionally, the RAN node may also be a server, a wearable device, a vehicle or an on-board device, etc. For example, the access network device in the vehicle to everything (V2X) technology may be a road side unit (RSU). The embodiments of the present application do not limit the specific technology and specific device form adopted by the network equipment.

[0091] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move based on the location of the mobile base station. In other examples, a helicopter or drone can be configured to act as a device that communicates with another base station.

[0092] In some deployments, the network devices mentioned in the embodiments of the present application may include a CU, a DU, or both a CU and a DU, or a control plane CU node (central unit-control plane (CU-CP)), a user plane CU node (central unit-user plane (CU-UP)), and a DU node. For example, the network devices may include a gNB-CU-CP, a gNB-CU-UP, and a gNB-DU.

[0093] In some deployments, multiple RAN nodes collaborate to assist terminals in achieving wireless access, with different RAN nodes implementing portions of the base station's functionality. For example, a RAN node can be a CU, DU, CU-CP, CU-UP, or RU. The CU and DU can be separate or included in the same network element, such as the BBU. The RU can be included in a radio frequency device or radio unit, such as an RRU, AAU, or RRH.

[0094] The RAN node may support one or more types of fronthaul interfaces, with different fronthaul interfaces corresponding to DUs and RUs with different functions. If the fronthaul interface between the DU and the RU is a common public radio interface (CPRI), the DU is configured to implement one or more baseband functions, and the RU is configured to implement one or more radio frequency functions. If the fronthaul interface between the DU and the RU is another type of interface, relative to the CPRI, some of the downlink and / or uplink baseband functions, such as precoding, digital beamforming (BF), or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix (CP) for downlink, are moved from the DU to the RU for implementation; and for 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 one possible implementation, the interface may be an enhanced common public radio interface (eCPRI). In the eCPRI architecture, the division between the DU and RU is different, corresponding to different types (category, Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, and F.

[0095] Taking eCPRI Cat A as an example, for downlink transmission, based on layer mapping, the DU is configured to implement layer mapping and one or more functions preceding it (i.e., one or more of coding, rate matching, scrambling, modulation, and layer mapping). Other functions after layer mapping (e.g., resource element (RE) mapping, digital beamforming (BF), or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix (CP) addition) are moved to the RU for implementation. For uplink transmission, based on RE demapping, the DU is configured to implement demapping and one or more functions preceding it (i.e., one or more of decoding, rate matching, descrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and RE demapping). Other functions after demapping (e.g., one or more of digital BF or fast Fourier transform (FFT) / CP removal) are moved to the RU for implementation. It is understandable that for the functional description of DU and RU corresponding to various types of eCPRI, reference can be made to the eCPRI protocol, which will not be described in detail here.

[0096] In one possible design, the processing unit for implementing baseband functions in the BBU is called a baseband high layer (BBH) unit, and the processing unit for implementing baseband functions in the RRU / AAU / RRH is called a baseband low layer (BBL) unit.

[0097] In different systems, 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, CU may also be called O-CU (Open CU), DU may also be called O-DU, CU-CP may also be called O-CU-CP, CU-UP may also be called O-CU-UP, and RU may also be called O-RU. Any unit of CU (or CU-CP, CU-UP), DU and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0098] In the embodiments of the present application, the device for implementing the functions of the network device can be a network device; it can also be a device that can support the network device to implement the functions, such as a chip system, a hardware circuit, a software module, or a hardware circuit and a software module. The device can be installed in the network device or used in conjunction with the network device. In the embodiments of the present application, only the device for implementing the functions of the network device is used as an example to illustrate, and does not constitute a limitation on the solutions of the embodiments of the present application.

[0099] The network device and / or terminal device can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; it can also be deployed on the water surface; it can also be deployed on aircraft, balloons and satellites in the air. The embodiments of this application do not limit the scenarios in which the network device and the terminal device are located. In addition, the terminal device and the network device can be hardware devices, or they can be software functions running on dedicated hardware, software functions running on general-purpose hardware, such as virtualization functions instantiated on a platform (e.g., a cloud platform), or entities including dedicated or general-purpose hardware devices and software functions. This application does not limit the specific forms of the terminal device and the network device.

[0100] In wireless communication networks, such as mobile communication networks, the services supported by the networks are becoming increasingly diverse, and therefore the demands that need to be met are becoming increasingly diverse. For example, the network needs to be able to support ultra-high speeds, ultra-low latency, and / or ultra-large connections. This feature makes network planning, network configuration, and / or resource scheduling increasingly complex. In addition, as network functionality becomes increasingly powerful, such as supporting higher spectrum, 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 demands, 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 wireless communication networks to achieve network intelligence.

[0101] In order to support AI technology in wireless networks, AI nodes may also be introduced into the network.

[0102] Optionally, the AI ​​node can be deployed in one or more of the following locations in the communication system: access network equipment, terminal equipment, or core network equipment. Alternatively, the AI ​​node can be deployed separately, for example, in a location other than any of the above devices, such as a host or cloud server in an over-the-top (OTT) system. The AI ​​node can communicate with other devices in the communication system, such as one or more of the following: network equipment, terminal equipment, or core network elements.

[0103] It is understood that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, the multiple AI nodes can be divided based on function, such as different AI nodes are responsible for different functions.

[0104] It can also be understood that AI nodes can be independent devices, or they can be integrated into the same device to implement different functions, or they can be network elements in hardware devices, or they can be software functions running on dedicated hardware, or they can be virtualized functions instantiated on a platform (for example, a cloud platform). This application does not limit the specific form of the above-mentioned AI nodes.

[0105] An AI node can be an AI network element or an AI module.

[0106] Figure 1 is a schematic diagram of a possible application framework in a communication system. As shown in Figure 1, network elements in the communication system are connected through interfaces (such as NG, Xn) or air interfaces. One or more AI modules are provided in one or more devices of these network element nodes, such as core network equipment, access network nodes (RAN nodes), terminals or OAM (for clarity, only one is shown in Figure 1). The access network node can be a separate RAN node, or it can include multiple RAN nodes, for example, including CU and DU. The CU and / or DU can also be provided with one or more AI modules. Optionally, the CU can also be split into CU-CP and CU-UP. One or more AI models are provided in the CU-CP and / or CU-UP.

[0107] The AI ​​module is used to implement the corresponding AI function. The AI ​​modules deployed in different network elements may be the same or different. The model of the AI ​​module can implement different functions according to different parameter configurations. The model of the AI ​​module can be configured based on one or more of the following parameters: structural parameters (such as the number of neural network layers, the width of the neural network, the connection relationship between layers, the weight of the neuron, the activation function of the neuron, or at least one of the bias in the activation function), input parameters (such as the type of input parameters and / or the dimension of the input parameters), or output parameters (such as the type of output parameters and / or the dimension of the output parameters). Among them, the bias in the activation function can also be called the bias of the neural network.

[0108] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or on the same node or device.

[0109] Figure 2 is a schematic diagram of a possible application framework in a communication system. As shown in Figure 2, the communication system includes a RAN intelligent controller (RIC). For example, the RIC can be the AI ​​modules 117 and 118 shown in Figure 1, which are used to implement AI-related functions. The RIC includes a near-real-time RIC (near-real time RIC, near-RT RIC) and a non-real-time RIC (non-real time RIC, Non-RT RIC). Among them, the non-real-time RIC mainly processes non-real-time information, such as data that is not sensitive to delay, and the delay of this data can be in the order of seconds. The real-time RIC mainly processes near-real-time information, such as data that is relatively sensitive to delay, and the delay of this data is in the order of tens of milliseconds.

[0110] The near real-time RIC is used for model training and reasoning. For example, it is used to train an AI model and use the AI ​​model for reasoning. The near real-time RIC can obtain network-side and / or terminal-side information from a RAN node (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or a terminal. This information can be used as training data or reasoning data. Optionally, the near real-time RIC can deliver the reasoning result to the RAN node and / or the terminal. Optionally, the reasoning 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 delivers the reasoning result to the DU, and the DU sends it to the RU.

[0111] The non-real-time RIC is also used for model training and reasoning. For example, it is used to train an AI model and use the model for reasoning. The non-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 reasoning data, and the reasoning results can be submitted to the RAN node and / or terminal. Optionally, the reasoning results can be exchanged between the CU and the DU, and / or between the DU and the RU. For example, the non-real-time RIC submits the reasoning results to the DU, and the DU sends it to the RU.

[0112] The near real-time RIC and non-real-time RIC may also be separately configured as a network element. Optionally, the near real-time RIC and non-real-time RIC may also be part of other devices. For example, the near real-time RIC is configured in a RAN node (e.g., a CU or DU), while the non-real-time RIC is configured in an OAM, a cloud server, a core network device, or other network device.

[0113] FIG3 is a schematic diagram of a communication system applicable to the communication method of an embodiment of the present application. As shown in FIG3 , the communication system 100 may include at least one network device, such as the network device 110 shown in FIG3 ; the communication system 100 may also include at least one terminal device, such as the terminal device 120 and the terminal device 130 shown in FIG3 . The network device 110 and the terminal device (such as the terminal device 120 and the terminal device 130) can communicate via a wireless link. The communication devices in the communication system, for example, the network device 110 and the terminal device 120, can communicate via multi-antenna technology.

[0114] Figure 4 is a schematic diagram of another communication system applicable to the communication method of an embodiment of the present application. Compared to the communication system 100 shown in Figure 3, the communication system 200 shown in Figure 4 also includes an AI network element 140. AI network element 140 is used to perform AI-related operations, such as constructing a training dataset or training an AI model.

[0115] In one possible implementation, the network device 110 may send data related to the training of the AI ​​model to the AI ​​network element 140, which constructs a training data set and trains the AI ​​model. For example, the data related to the training of the AI ​​model may include 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: an AI model that has completed training, an evaluation result or a test result of the model, etc. Exemplarily, a portion of the trained AI model may be deployed on the network device 110, and another portion may be deployed on the terminal device. Alternatively, the trained AI model may be deployed on the network device 110. Alternatively, the trained AI model may be deployed on the terminal device.

[0116] It should be understood that Figure 4 illustrates only the example of a direct connection between AI network element 140 and network device 110. In other scenarios, AI network element 140 may also be connected to a terminal device. Alternatively, AI network element 140 may be connected to both network device 110 and a terminal device simultaneously. Alternatively, AI network element 140 may be connected to network device 110 through a third-party network element. This embodiment of the present application does not limit the connection relationship between the AI ​​network element and other network elements.

[0117] The AI ​​network element 140 may also be provided as a module in a network device and / or a terminal device, for example, in the network device 110 or the terminal device shown in FIG3 .

[0118] It should be noted that Figures 3 and 4 are simplified schematic diagrams for ease of understanding. For example, the communication system may also include other devices, such as wireless relay devices and / or wireless backhaul devices, which are not shown in Figures 3 and 4. In actual applications, the communication system may include multiple network devices and 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.

[0119] To facilitate understanding of the solutions of the embodiments of the present application, the terms that may be involved in the embodiments of the present application are explained below.

[0120] 1. Artificial Intelligence: This refers to the ability of machines to learn, accumulate experience, and solve problems that humans can solve through experience, such as natural language understanding, image recognition, and chess. Artificial Intelligence can be understood as the intelligence exhibited by machines created by humans. Generally, AI refers to the technology that represents human intelligence through computer programs. The goals of AI include understanding intelligence by constructing computer programs that can perform symbolic reasoning or deduction.

[0121] 2. Machine learning: This is an implementation of artificial intelligence. Machine learning is a method that empowers machines to learn, enabling them to perform functions that cannot be accomplished through direct programming. In practical terms, machine learning utilizes data to train models and then uses these models to make predictions. There are many machine learning methods, such as neural networks (NNs), decision trees, and support vector machines. Machine learning theory primarily involves the design and analysis of algorithms that enable computers to learn automatically. Machine learning algorithms automatically analyze data to identify patterns and use these patterns to make predictions about unknown data.

[0122] 3. Neural Network: A specific embodiment of machine learning. A neural network is a mathematical model that processes information by mimicking the behavioral characteristics of animal neural networks. The concept of a neural network is derived from the neuronal structure of the brain. Each neuron performs a weighted sum operation on its input values, and the result of this weighted summation is passed through an activation function to generate an output.

[0123] Neural networks generally comprise a multi-layer structure, with each layer comprising one or more logical decision units, referred to as neurons. Increasing the depth and / or width of a neural network can enhance its expressive power, providing more powerful information extraction and abstract modeling capabilities for complex systems. The depth of a neural network can be understood as the number of layers it comprises, and the number of neurons in each layer can be referred to as the width of that layer. In one possible implementation, a neural network comprises an input layer and an output layer. The input layer of the neural network processes the input through neurons and then passes the result to the output layer, which then obtains the output of the neural network. In another possible implementation, a neural network comprises an input layer, a hidden layer, and an output layer. The input layer of the neural network processes the input through neurons and then passes the result to an intermediate hidden layer. The hidden layer then passes the calculation result to the output layer or an adjacent hidden layer, which then obtains the output of the neural network. A neural network can comprise one or more sequentially connected hidden layers, without limitation.

[0124] During neural network training, a loss function can be defined. This function measures the difference between the model's predicted value and the actual value. During neural network training, the loss function describes the gap or discrepancy between the neural network's output and the ideal target value. Neural network training involves adjusting neural network parameters to ensure that the loss function's value is below a threshold or meets the target requirement. Neural network parameters can include at least one of the following: the number of neural network layers, their width, neuron weights, and parameters in the neuron activation function.

[0125] Taking the AI ​​model type as a neural network as an example, the AI ​​model involved in this disclosure can be a deep neural network (DNN). Depending on the network construction method, DNN can include feedforward neural networks (FNN), convolutional neural networks (CNN), and recurrent neural networks (RNN).

[0126] 4. Deep neural network: A neural network with multiple hidden layers.

[0127] 5. Deep learning: Machine learning using deep neural networks.

[0128] 6. AI Model

[0129] An AI model is an algorithm or computer program that implements AI functionality. It represents the mapping between the model's inputs and outputs. 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.

[0130] Exemplarily, the AI ​​model in the embodiment of the present application may include an encoder and a decoder. The encoder and decoder are used in combination, and it can be understood that the encoder and decoder are matching AI models. The encoder and decoder can be deployed on terminal devices and network devices respectively. In one possible design, a set of matched encoders (encoder) and decoders (decoder) can be specifically two parts of the same auto-encoder (AE), for example, as shown in Figure 5. The AE model in which the encoder and decoder are deployed on different nodes is a typical bilateral model. The encoder and decoder of the AE model are usually matched with a jointly trained encoder and decoder. The encoder processes the input V to obtain the processed result z, and the decoder can decode the encoder output z into the desired output V'.

[0131] Alternatively, the AI ​​model in the embodiment of the present application may be a single-ended model, which may be deployed on a terminal device or a network device.

[0132] 7. Training data set and inference data:

[0133] In the field of machine learning, ground truth usually refers to data that is believed to be accurate or real.

[0134] A training dataset is used to train an AI model. It may include the input to the AI ​​model, or the input and target output of the AI ​​model. A training dataset includes one or more training data. Training data may include training samples input to the AI ​​model, or the target output of the AI ​​model. The target output may also be referred to as a label, sample label, or labeled sample. A label is the true value.

[0135] In the communications field, training datasets can include simulated data collected through simulation platforms, experimental data collected in experimental scenarios, or measured data collected in actual communication networks. Because the geographical environments and channel conditions in which data are generated vary, such as indoor and outdoor locations, mobile speeds, frequency bands, or antenna configurations, the collected data can be categorized during acquisition. For example, data with the same channel propagation environment and antenna configuration can be grouped together.

[0136] Model training essentially involves learning certain characteristics from training data. When training an AI model (such as a neural network), the goal is to ensure that the model's output is as close as possible to the desired predicted value. This is done by comparing the network's predictions with the desired target values. The weight vectors of each layer of the AI ​​model are then updated based on the difference between the two. (Of course, before the first update, there's usually an initialization process, which pre-configures the parameters for each layer of the AI ​​model.) For example, if the network's prediction is too high, the weight vectors are adjusted to predict a lower value. This adjustment is repeated until the AI ​​model predicts the desired target value, or a value very close to it. Therefore, it's necessary to predefine how to compare the difference between the predicted and target values. This is known as the loss function, or objective function. These are important equations used to measure the difference between the predicted and target values. For example, a higher loss function indicates a greater difference. Therefore, training an AI model becomes a process of minimizing this loss, keeping the loss function below a threshold or ensuring that the loss function meets the target requirement. For example, the AI ​​model is a neural network, and adjusting the model parameters of the neural network includes adjusting at least one of the following parameters: the number of layers, width, weights of neurons, or parameters in the activation function of neurons of the neural network.

[0137] Inference data can be used as input to a trained AI model for inference. During the inference process, the inference data is input into the AI ​​model, and the corresponding output is the inference result.

[0138] 8. AI model design:

[0139] The design of an AI model primarily involves data collection (e.g., collecting training data and / or inference data), model training, and model inference. Furthermore, it can also include the application of inference results.

[0140] FIG6 shows an AI application framework.

[0141] In the aforementioned data collection phase, the data source is used to provide training datasets and inference data. In the model training phase, an AI model is obtained by analyzing or training the training data provided by the data source. The AI ​​model represents the mapping relationship between the model's input and output. Learning the AI ​​model through the model training node is equivalent to learning the mapping relationship between the model's input and output 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, obtaining an inference result. This phase can also be understood as inputting the inference data into the AI ​​model and obtaining an output from the AI ​​model, which is the inference result. The inference result can indicate the configuration parameters used (executed) by the execution object and / or the operations performed by the execution object. In the inference result application phase, the inference result is published. For example, the inference result can be centrally planned by the execution (actor) entity, for example, the execution entity can send the inference result to one or more execution objects (e.g., network devices or terminal devices) for execution. Alternatively, the execution entity can provide feedback on the model's performance to the data source to facilitate subsequent model update and training.

[0142] It is understandable that a communication system may include network elements with artificial intelligence capabilities. The above-mentioned AI model design-related steps can be performed by one or more network elements with artificial intelligence capabilities. In one possible design, AI functions (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 AI model training and / or inference. For example, the existing network element can be a network device or a terminal device. Alternatively, in another possible design, an independent network element can be introduced into the communication system to perform AI-related operations, such as training an AI model. The independent network element can be referred to as an AI network element or an AI node, etc., and the embodiments of the present application are not limited to these names. For example, the AI ​​network element can be directly connected to the network equipment in the communication system, or it can be indirectly connected to the network equipment through a third-party network element. 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 element, without limitation. Exemplarily, the independent network element can be deployed on one or more of the following: the network device side, the terminal device side, or the core network side. Optionally, it can be deployed on a cloud server. Exemplarily, the communication system shown in FIG4 introduces an AI network element 140.

[0143] The training process of different models can be deployed in different devices or nodes, or in the same device or node. The inference process of different models can be deployed in different devices or nodes, or in the same device or node. Taking the completion of the model training phase of a terminal device as an example, the terminal device can train the matching encoder and decoder, and then send the model parameters of the decoder to the network device. Taking the completion of the model training phase of a network device as an example, after the network device trains the matching encoder and decoder, it can indicate the model parameters of the encoder to the terminal device. Taking the completion of the model training phase of an independent AI network element as an example, the AI ​​network element can train the matching encoder and decoder, and then send the model parameters of the encoder to the terminal device and the model parameters of the decoder to the network device. Then, the model inference phase corresponding to the encoder is performed in the terminal device, and the model inference phase corresponding to the decoder is performed in the network device.

[0144] Among them, the model parameters may include one or more of the following structural parameters of the model (such as the number of layers and / or weights of the model, etc.), the input parameters of the model (such as input dimension, number of input ports), or the output parameters of the model (such as output dimension, number of output ports). It can be understood that the input dimension may refer to the size of an input data. For example, when the input data is a sequence, the input dimension corresponding to the sequence may indicate the length of the sequence. The number of input ports may refer to the number of input data. Similarly, the output dimension may refer to the size of an output data. For example, when the output data is a sequence, the output dimension corresponding to the sequence may indicate the length of the sequence. The number of output ports may refer to the number of output data.

[0145] 9. Model training: The process of selecting a suitable loss function and using an optimization algorithm to train the model parameters so that the value of the loss function is less than the threshold, or the value of the loss function meets the target requirements.

[0146] 10. Model application: Use the trained model to solve practical problems.

[0147] At present, 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 one-sided model, if there are different models on the UE side that meet different needs, it is necessary to obtain the association between a set of data sets and the AI ​​model through the input and output of the AI ​​model. Or the association between a set of data sets and the AI ​​model is obtained through the correspondence between the input and output. For example, in AI-based sparse beam management, the input is often determined by scanning a subset of all beams to obtain the RSRP, and the output predicted by the model is the information of all beams, which can be the predicted RSRP of all beams or the probability that each beam in all beams becomes the optimal beam. Or the correspondence between each input and output and the AI ​​model can be identified through the quasi-colocation (QCL) relationship corresponding to the input and output. Alternatively, the correspondence between the input and output and the AI ​​model can be obtained through more direct information, such as the beam shape and beamwidth of the network-side beam in beam management.

[0148] That is, in order to train the AI ​​model, the UE needs 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 private information on the network side. For example, taking beam management training as an example, the relevant information of beam management involves how the network side configures the transmit beams for different AI model inputs and the arrangement of all beams, exposing private information on the network side.

[0149] In view of this, the present application proposes a communication method that can avoid the leakage of private information of network devices by grouping training data and issuing the training data required by the AI ​​model.

[0150] 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 refers to configuration by the network device, such as the network device configuring the resource pool information. Pre-configuration means that the communication system is pre-defined (such as the communication system pre-defines the resource pool information), or the communication protocol is pre-defined (such as the communication protocol pre-defines the resource pool information), or the terminal device is pre-configured when it leaves the factory (such as the terminal device pre-configures the resource pool information when it leaves the factory), or configured by the high-level signaling of the terminal device (such as radio resource control (RRC) signaling).

[0151] It should be understood that, in this application, indication includes direct indication (also known as explicit indication) and implicit indication. Direct indication of information A refers to including information A; implicit indication of information A refers to indicating information A through the correspondence between information A and information B and the direct indication of information B. The correspondence between information A and information B can be predefined, pre-stored, pre-burned, or pre-configured.

[0152] It should be understood that, in this application, information C is used to determine information D, which includes both information D being determined solely based on information C and information D being determined based on information C and other information. Furthermore, information C can also be used to determine information D indirectly, for example, where information D is determined based on information E, and information E is determined based on information C.

[0153] In addition, "device A sends information A to device B" in each embodiment of the present application can be understood as the destination end of the information A or the intermediate device in the transmission path between the destination end and the device B, which may include directly or indirectly sending information to device B. "Device B receives information A from device A" can be understood as the source end of the information A or the intermediate device in the transmission path between the source end and the source end is device A, which may include directly or indirectly receiving information from device A. The information may be processed as necessary between the source end and the destination end of the information transmission, such as format changes, etc., but the destination end can understand the valid information from the source end. Similar expressions in this application can be understood similarly and will not be elaborated here. The devices and apparatuses in this application can be understood interchangeably.

[0154] It should be understood that the communication method of the present application can be applied between network devices, between terminal devices, and between network devices and terminal devices. The following description uses network devices (such as a first network device and a second network device) and terminal devices (such as a first training device and a second training device, for example, the training device can be a UE) as examples of execution entities.

[0155] As shown in FIG7 , the method includes the following steps:

[0156] S710: A first network device obtains first data.

[0157] The first data belongs to at least one data set, and the at least one data set is used to train 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.

[0158] Each data set in the at least one data set corresponds to an AI model. In one possible implementation, the types of AI models can be divided according to the functions of the AI ​​models. For example, the AI ​​model used for beam management training is one AI model, and the AI ​​model used for positioning training is another AI model. In other words, at least one data set corresponds to the function of at least one AI model. For example, data set A corresponds to the AI ​​model for beam management training, and data set B corresponds to the AI ​​model for positioning training. The above "corresponds to" can be understood as "used for", for example, the data included in data set A is the data used for beam management training, or it can be said that the data included in data set A can be used as the input of the AI ​​model for beam management training.

[0159] The at least one dataset may also be at least one data group. In the embodiments of the present application, there is no limitation on the form of multiple data, and a dataset or a data group may also be referred to as multiple data.

[0160] The first data is data in at least one dataset. Furthermore, the first data is data in a first dataset, and the first dataset belongs to at least one dataset. For example, there are three datasets, corresponding to three AI models: 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 data in dataset C.

[0161] The first data may be part of the data in the first data set. For example, the first data set includes 4 data, and the first data may be one data, two data, or three data.

[0162] The first data may also be all the data in the first data set. For example, if the first data set includes 4 data, the first data includes the 4 data.

[0163] The correspondence between the above different data sets and different AI models can be preset or configured. The configuration method is described below.

[0164] In one possible approach, the training device reports characteristic information to the first network device. The characteristic information may be information of the training device itself or characteristic information of the AI ​​model of the training device.

[0165] Specifically, the information of the training device itself can be the identification 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 cycle is the computing power of the training device. The identification of the training device, which can be the brand of the training device, or the index of the training device are only examples. Other methods that can uniquely identify the training device are also applicable to this application and should be within the scope of protection of this application.

[0166] The characteristic information of the AI ​​model may 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, wherein the training requirements of the AI ​​model may be the type of required data set, the size of the required data set, the characteristics of the required data set, and the like. The type of the required data set may be the purpose of the data set, such as a certain type of data set is used for training beam management, and another type of data set is used for training positioning. The size of the required data set can be understood as the amount of data contained in the required data set. For example, if a data set contains 100,000 data, the size of the data set is 100,000 (W). The characteristics of the required data set may be the commonality of the data contained in the data set.

[0167] The first network device can allocate data based on the above-mentioned characteristic information. That is, the first network device determines the first data from at least one data set based on the first information. For example, the first network device allocates data from the first data set to AI model A and allocates data from the second data set to AI model B. Furthermore, the first network device can also determine the size of the allocated data for different training devices based on the above-mentioned characteristic 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 based on the number of first information corresponding to the first AI model and the total amount of data corresponding to the first AI model. For example, the size of the total data set allocated to support the training of an 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 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.

[0168] Optionally, the data allocation step may be performed by a second network device, such as a core network. In this case, the first network device reports the collected feature information to the core network (i.e., the first network device sends the fourth information to the second network device), and the core network allocates data to different training devices. The specific data allocation method can be referenced above with respect to the allocation method of the first network device and is not further described here.

[0169] One possible implementation is that 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 needs of different cells and defines the corresponding resource allocation. For example, assuming that the size of the data set required for training each AI model is 10W, cell 1 has more training devices that need to collect beam management-related data sets, which accounts for about 80% of all training devices that need to train beam management-related models. The core network notifies the first network device A to transmit 8W subsets of the data set for beam management. The allocation of data sets for other cells is similar. For positioning training, relevant data can also be allocated based on the reported information.

[0170] It's worth noting that the core network only carries the assigned tasks and doesn't transfer the dataset. For example, the core network only needs to notify the first network device of the number of datasets to transfer for a particular training feature, while the first network device itself performs the dataset transfer function. For example, the second network device sends fifth information to the first network device, indicating the size of the first data. The size of the first data is determined based on 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.

[0171] Another possible implementation is that the core network can serve as the communication medium for over-the-top (OTT) services. This allows the core network to directly obtain the feature information of the training device for different AI models through the OTT server, without having to report the feature information through the first network device. This further shortens the communication process, reduces device power consumption, and helps reduce communication latency.

[0172] S720: The first network device sends first data to the first training apparatus. Correspondingly, the first training apparatus receives the first data.

[0173] For example, the first network device sends first data to the first training apparatus through a data channel.

[0174] Optionally, there may be multiple training devices. The first network device can send data to the multiple training devices through a data channel. 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 set is a part of the data in the first data set, and the second data is another part of the data in 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 AI ​​models corresponding to the first training device and the second training device have the same characteristics, for example, both are used for positioning training.

[0175] Specifically, the first training device and the second training device are classified together because they have the same AI model training requirements, and the first network device sends different data sets for the same model or requirement training to them through the data channel. At this time, different subsets of 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. The composition method of the data set may be the input reference signal receive power (RSRP) and the output RSRP or the identity (ID) of the optimal beam. Based on this, the single data set received by the first training device may be [RSRP_1, ID_1], and the data set received by the second training device may be [RSRP_2, ID2]. It is also worth noting 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 supporting training with the same AI model. Of course, the data of the first training device and the second training device may also be the same, and this application does not limit this.

[0176] In addition, the characteristics of the AI ​​models of the first and second training devices may be different. For example, the first training device corresponds to AI model A, which is used for positioning training. The second training device corresponds to AI model B, which 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 data from the first dataset, and the second data is data from the second dataset. In other words, the input of the first training device and the input of the second training device belong to different datasets.

[0177] Optionally, the method may further include the following steps:

[0178] S730: The first training apparatus sends second information to the first network device. Correspondingly, the first network device receives the second information.

[0179] 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.

[0180] That is, the first network device can transmit the data corresponding to the AI ​​model through the data channel, and the training device can determine and provide feedback on whether the required amount of data has been received, and can also synchronize the progress of receiving data. This method is suitable for situations where the first network device has not allocated data volume to the training device. When the first network device has determined the data volume for different training devices, the first network device can determine whether the data received by the first training device is sufficient for training the first AI model.

[0181] When the first network device determines that data transmission is complete, or the second information received by the first network device indicates that the data received by the first training device is sufficient for training the first AI model, the first network device may further send a third message to the first training device. In response, the first training device receives the third message, which indicates the end of the first data transmission. In other words, the third message is used to indicate the completion of the data transmission.

[0182] It should be understood that the completion of data transmission on one training device does not affect data transmission on other training devices. For example, if a first training device receives the third message, data transmission on the first training device is complete, but data transmission on the second training device, or other training devices, such as the third training device, can continue until data transmission is complete.

[0183] At the same time, corresponding indication information can be configured in the transmitted data to indicate the purpose of the data, such as indicating which data in a set of data sets are used to obtain the input of the AI ​​model and which data are used to obtain the output of the AI ​​model.

[0184] S740: The first training device trains a first AI model based on the first data.

[0185] For example, the training device can integrate and train the received data based on the training device's own mechanism. The training device can train the received data locally. Training can also be performed non-locally. For example, all data can be uploaded to the OTT server of the training device, and the OTT server integrates the data and trains the AI ​​model. After the model training is completed, the corresponding AI model can be issued or configured to each training device. Specifically, the method of training the AI ​​model by the training device can refer to the existing technology and will not be described in detail in this application.

[0186] In this method, network devices transmit data to training devices over air interfaces, preventing the leakage of private information. Furthermore, the network devices classify training data to meet different training requirements and deliver corresponding training data for different training models, further reducing the complexity of the training device acquiring the required data and saving device power consumption.

[0187] To facilitate understanding of the communication method of the present application, two exemplary implementation processes are given below.

[0188] Implementation 1: Taking the first network device as a gNB as an example, UE1 as an example of a first training device, UE2 as an example of a second training device, and UE3 as an example of a third training device, as shown in FIG8 , this implementation includes the following steps:

[0189] S810: UE1 sends Feature 1 to the gNB. In response, the gNB receives Feature 1.

[0190] S820: UE2 sends Feature 2 to the gNB. In response, the gNB receives Feature 2.

[0191] S830: UE3 sends feature 3 to gNB, and gNB receives feature 3 accordingly.

[0192] The above-mentioned feature 1, feature 2 and feature 3 can refer to the description of the feature information (or first information) in S710, which will not be repeated here.

[0193] S840: The gNB groups different UEs according to their characteristic information.

[0194] For example, the gNB divides three UEs into two groups based on the purpose of the AI ​​model. For example, UE1 and UE2 belong to 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.

[0195] At S850, the gNB groups the data according to the feature information.

[0196] For example, the gNB categorizes data based on the AI ​​model's purpose. For example, dataset A is used for positioning training, while dataset B is used for beam management training. The specific data classification method is described in S710 and is not further explained here.

[0197] S860: The gNB sends data A to UE1. UE1 receives data A accordingly.

[0198] S870: gNB sends data B to UE2, and correspondingly, UE1 receives data B.

[0199] Among them, data A and data B belong to the same dataset.

[0200] At S880, the gNB sends data C to UE3, and correspondingly, UE1 receives the data C.

[0201] The dataset to which data C belongs is different from the datasets to which data A and data B belong.

[0202] S890: The gNB determines whether the data transmission is completed.

[0203] S8100: The gNB sends a data transmission completion indication to UE1. Correspondingly, UE1 receives the data transmission completion indication.

[0204] S8110: The gNB sends a data transmission completion indication to UE2. Correspondingly, UE2 receives the data transmission completion indication.

[0205] The data transmission completion indication is an example of the third information.

[0206] 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 a data transmission completion indication is sent to UE3.

[0207] S8120: The UE trains an AI model based on the received data.

[0208] In this implementation, S810 to S840, S8100, and S8110 are all optional steps.

[0209] 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, thereby avoiding the leakage of private information of the network device.

[0210] Implementation 2: For example, the first network device is gNB1, the second network device is the core network, and the third network device is gNB2. UE1 is used as the first training device, UE2 is used as the second training device, UE3 is used as the third training device, and UE4 is used as the fourth training device. UE1 and UE2 belong to the first cell, where the base station is gNB1. UE3 and UE4 belong to the second cell, where the base station is gNB2.

[0211] As shown in Figure 9, the implementation includes the following steps:

[0212] S910: UE1 sends feature 1 to gNB1. Correspondingly, gNB1 receives feature 1.

[0213] S920, UE2 sends feature 2 to gNB1, and correspondingly, gNB1 receives feature 2.

[0214] S930: UE3 sends feature 3 to gNB2. Correspondingly, gNB2 receives feature 3.

[0215] S940: UE4 sends feature 4 to gNB2. Correspondingly, gNB2 receives feature 4.

[0216] The above-mentioned features 1, 2, 3 and 4 can refer to the description of the feature information (or first information) in S710 and will not be repeated here.

[0217] At step S950, gNB1 sends cell information to the core network, and the core network receives the cell information accordingly.

[0218] S960, gNB2 sends cell information to the core network, and correspondingly, the core network receives the cell information.

[0219] The cell information may include the number of UEs included in the cell and the above-mentioned feature information.

[0220] S970: The core network groups the UEs.

[0221] For example, the core network groups UEs according to the usage of their AI models, such as UE1 and UE4 are grouped together, and UE2 and UE3 are grouped together.

[0222] S980, core network allocates data.

[0223] For details, please refer to the data allocation method in S710, which will not be described in detail.

[0224] S990: The core network sends indication information A to gNB1. Correspondingly, gNB1 receives indication information A.

[0225] The indication information A indicates data allocated to UE1 and UE2, such as the size of the data.

[0226] S9100: The core network sends indication information B to gNB2. Correspondingly, gNB1 receives indication information B.

[0227] The indication information B indicates data allocated to UE3 and UE4, such as the size of the data.

[0228] The indication information A and the indication information B are examples of fifth information.

[0229] S9110, gNB1 sends data 1 to UE1, and correspondingly, UE1 receives data 1.

[0230] S9120, gNB1 sends data 2 to UE2, and correspondingly, UE2 receives data 2.

[0231] S9130, gNB2 sends data 3 to UE3, and correspondingly, UE3 receives data 3.

[0232] S9140, gNB2 sends data 4 to UE4, and correspondingly, UE4 receives data 4.

[0233] Optionally, when data transmission is completed, the gNB may also send an indication message to the UE corresponding to the data, indicating the end of data transmission.

[0234] S9150: Each UE trains an AI model based on the received data.

[0235] In this implementation, the core network coordinates UEs and data in different cells, and the gNB is responsible for air interface transmission of data. It is suitable for scenarios with multiple training devices and multiple cells.

[0236] The various implementations described in this document may be independent solutions or may be combined according to internal logic, and all of these solutions fall within the scope of protection of this application.

[0237] In the embodiments provided in the present application, the methods provided in the embodiments of the present application are introduced from the perspective of interaction between various devices. In order to implement the various functions in the methods provided in the embodiments of the present application, the network device or terminal device may include a hardware structure and / or a software module to implement the above functions in the form of a hardware structure, a software module, or a hardware structure plus a software module. Whether a function of the above functions is executed in the form of a hardware structure, a software module, or a hardware structure plus a software module depends on the specific application and design constraints of the technical solution.

[0238] The division of modules in the embodiments of the present application is illustrative and is merely a logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional modules in the various embodiments of the present application may be integrated into a single processor, or may exist physically separately, or two or more modules may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or software functional modules.

[0239] Similar to the above concept, as shown in FIG10 , an embodiment of the present application further provides an apparatus 1000 for implementing the functions of the transmitting device or receiving device in the above method. For example, the apparatus may be a software module or a chip system. In the embodiment of the present application, the chip system may be composed of a chip or may include a chip and other discrete components. The apparatus 1000 may include: a processing unit 1010 and a communication unit 1020.

[0240] In the embodiment 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 embodiment.

[0241] The communication device provided in the embodiment of the present application is described in detail below with reference to Figures 10 to 12. It should be understood that the description of the device embodiment corresponds to the description of the method embodiment. Therefore, for matters not described in detail, reference can be made to the method embodiment above. For the sake of brevity, they will not be repeated here.

[0242] A communication unit may also be referred to as a transceiver, transceiver, or transceiver device. A processing unit may also be referred to as a processor, processing board, processing module, or processing device. Optionally, the device in communication unit 1020 that implements the receiving function may be considered a receiving unit, and the device in communication unit 1020 that implements the transmitting function may be considered a transmitting unit. That is, communication unit 1020 includes both a receiving unit and a transmitting unit. A communication unit may also be referred to as a transceiver, transceiver, or interface circuit. A receiving unit may also be referred to as a receiver, receiver, or receiving circuit. A transmitting unit may also be referred to as a transmitter, transmitter, or transmitting circuit.

[0243] When the communication device 1000 performs the function of the network device in the process shown in FIG. 7 in the above embodiment:

[0244] The communication unit is used to send and receive information, such as sending data, receiving first information, receiving second information, sending third information, sending fourth information, receiving fifth information, etc.

[0245] A processing unit is used to obtain data.

[0246] When the communication device 1000 performs the function of the training device in any of the processes shown in FIG. 7 in the above embodiments:

[0247] Processing unit, used for training AI models based on data, etc.

[0248] The communication unit is used to send and receive information, for example, to receive data or third-party information.

[0249] The above are just examples. The processing unit 1010 and the communication unit 1020 can also perform other functions. For more detailed descriptions, please refer to the method embodiment shown in Figure 3 or related descriptions in other method embodiments, which are not repeated here.

[0250] As another possible product form, the transmitting device and receiving device described in the embodiment of the present application can be implemented by a general bus architecture. For ease of explanation, refer to Figure 11, which is a structural diagram of a communication device 1100 provided in an embodiment of the present application, and 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 chip system therein; or, the communication device 1100 can be a second terminal device, or a chip or module therein; or, the communication device 1100 can be a third terminal device, or a chip or module therein; or, the communication device 1100 can be a fourth terminal device, or a chip or module therein; or, the communication device 1100 can be a fifth terminal device, or a chip or module therein; or, the communication device 1100 can be a sixth terminal device, or a chip or module therein. Figure 11 only shows the main components of the communication device 1100. 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).

[0251] Optionally, the processor 1101 is primarily used to process communication protocols and communication data, as well as control the entire communication device, execute software programs, and process software program data. The memory 1103 is primarily used to store software programs and data. The transceiver 1102 may include a radio frequency circuit and an antenna. The radio frequency circuit is primarily used to convert baseband signals into radio frequency signals and process radio frequency signals. The antenna is primarily used to transmit and receive radio frequency signals in the form of electromagnetic waves. Input and output devices, such as a touch screen, display, and keyboard, are primarily used to receive user input and output data to the user.

[0252] Optionally, the processor 1101 , the transceiver 1102 , and the memory 1103 may be connected via a communication bus.

[0253] When 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 sent wirelessly, the processor 1101 performs baseband processing on the data to be sent and outputs the 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 to the outside 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.

[0254] In another implementation, the RF circuit and antenna may be provided independently of the processor performing baseband processing. For example, in a distributed scenario, the RF circuit and antenna may be remotely arranged independent of the communication device.

[0255] In some embodiments, in terms of hardware implementation, those skilled in the art may conceive that the above-mentioned communication device 110 may take the form of the communication device 1100 shown in FIG. 11 .

[0256] As an example, the functions / implementation process of the processing module 1020 in FIG11 can be implemented by the processor 1101 in the communication device 1100 shown in FIG11 calling the computer-executable instructions stored in the memory 1103. The functions / implementation process of the transceiver module 1010 in FIG11 can be implemented by the transceiver 1102 in the communication device 1100 shown in FIG11.

[0257] As another possible product form, the first terminal device, second terminal device, third terminal device, fourth terminal device, fifth terminal device, or sixth terminal device in this application may adopt the structure shown in Figure 12, or include the components shown in Figure 12. Figure 12 is a schematic diagram of the structure of a communication device 1200 provided in this application.

[0258] As shown in FIG12 , the communication device 1200 includes at least one processor 1201. Optionally, the communication device further includes a communication interface 1202.

[0259] When the program instructions are executed in the at least one processor 1201, the apparatus 1200 may implement the method provided in any of the aforementioned embodiments and any possible designs thereof. Alternatively, the processor 1201 may implement the method provided in any of the aforementioned embodiments and any possible designs thereof through logic circuits or by executing code instructions.

[0260] 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 with other communication devices, such as exchanging control signaling and / or service data. Exemplarily, the communication interface 1202 can be used to receive signals from devices other than the communication device 1200 and transmit them to the processor 1201, or to send signals from the processor 1201 to other communication devices other than the communication device 1200.

[0261] Optionally, the communication interface 1202 may be a code and / or data read and write interface circuit, or the communication interface 1202 may be a signal transmission interface circuit between a communication processor and a transceiver, or a pin of a chip.

[0262] Optionally, the communication device 1200 may further include at least one memory 1203, which may be used to store 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 within or outside the communication device 1200, without limitation.

[0263] 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 in the same chip as the processor 1201, or in another chip other than the chip where the processor 1201 is located.

[0264] Optionally, the communication device 1200 may further include a bus 12011 , and various parts of the communication device 1200 may be interconnected via the bus 12011 .

[0265] In some embodiments, in terms of hardware implementation, those skilled in the art may conceive that the communication device 110 shown in FIG. 11 may take the form of the communication device 1200 shown in FIG. 12 .

[0266] As an example, the functions / implementation process of the processing module 1020 in FIG11 can be implemented by the processor 1201 in the communication device 1200 shown in FIG12 calling the computer-executable instructions stored in the memory 1203. The functions / implementation process of the transceiver module 1010 in FIG11 can be implemented by the communication interface 1202 in the communication device 1200 shown in FIG12.

[0267] It should be noted that the structure shown in Figure 12 does not constitute a specific limitation on the transmitting device and the receiving device. For example, in other embodiments of the present application, the transmitting device and the second terminal device may include more or fewer components than shown, or combine or separate certain components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0268] When the communication device is a chip used in 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 in the terminal device (such as a radio frequency module or antenna), and the information is sent by the network device to the terminal device; or the terminal device chip sends information to other modules in the terminal device (such as a radio frequency module or antenna), and the information is sent by the terminal device to the network device.

[0269] When the communication device is a chip used in a network device, the network device chip implements the network device functions of the above method embodiments. The network device chip receives information from other modules in the network device (such as a radio frequency module or antenna), and the information is sent by the terminal device to the network device; or the network device chip sends information to other modules in the network device (such as a radio frequency module or antenna), and the information is sent by the network device to the terminal device.

[0270] It is understood that the processor in the embodiments of the present application may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), 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.

[0271] In the embodiments of the present application, the processor can be a random access memory (RAM), a flash memory, a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a register, a hard disk, a mobile hard disk, a CD-ROM, or any other form of storage medium well known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be an integral part of the processor. The processor and the storage medium can be located in an ASIC. In addition, the ASIC can be located in a network device or a terminal device. Of course, the processor and the storage medium can also exist in a network device or a terminal device as discrete components.

[0272] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, optical storage, etc.) that contain computer-usable program code.

[0273] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each flow and / or box in the flow chart and / or block diagram, as well as the combination of the flow chart and / or box in the flow chart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more flow charts and / or one or more boxes in the block diagram.

[0274] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0275] Obviously, those skilled in the art may make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include these modifications and variations.

[0276] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A communication method, characterized in that: Applicable to a first training device, comprising: 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 training at least one artificial intelligence (AI) model; A first AI model is trained based on the first data, where the first AI model belongs to the at least one AI model.

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

3. The method according to claim 2, characterized in that 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.

4. The method according to any one of claims 1 to 3, characterized in that The method further comprises: Sending second information to the first network device, wherein 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.

5. The method according to claim 4, characterized in that The second information further indicates a reception progress of the first data.

6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: Third information is received, where the third information indicates that the first data transmission is finished.

7. A communication method, applied to a first network device, characterized in that: include: Obtaining first data, where the first data belongs to at least one dataset, the at least one dataset is used for training 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; First data is sent to a first training device.

8. The method according to claim 7, characterized in that The method further comprises: First information is received from the first training device, where the first information indicates characteristic information of the first training device, or the first information indicates characteristic information of the first AI model.

9. The method according to claim 8, characterized in that 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.

10. The method according to claim 9, characterized in that The acquiring of the first data includes: The first data is determined 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 comprises: Receive N first information from N training devices, wherein the N first information respectively indicate characteristic information of the N training devices, or the N first information respectively indicate characteristic information of M AI models, Determining the first data includes: The size of the first data is determined according to the amount of 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 comprises: 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 to train the first AI model, or has not received the amount of data required to train the first AI model.

13. The method according to claim 12, characterized in that The second information further indicates a reception progress of the first data.

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

15. The method according to claim 9, characterized in that The method further comprises: Send fourth information to the second network device, where the fourth information indicates characteristic information of the N training devices, or characteristic information of the M first AI models.

16. The method according to claim 15, characterized in that The acquiring of the first data includes: receiving fifth information from the second network device, where the fifth information indicates a size of the first data, where the size of the first data is determined based on a total amount of data corresponding to the first AI model and N; The first data is obtained according to the fifth information.

17. A communication method, applied to a second network device, characterized in that: include: receiving fourth information, where the fourth information indicates characteristic information of N training devices, or characteristic information of M first AI models, where the first AI model belongs to at least one AI model; First data is determined based on the fourth information and at least one data set, where the at least one data set is used for training at least one AI model, and the first data is used for training a first AI model.

18. The method according to claim 17, characterized in that Determining the first data according to the fourth information and at least one data set includes: The size of the first data is determined based on the total amount of data corresponding to the first AI model and 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 comprises: Fifth information is sent, where the fifth information indicates the size of the first data.

20. A communication device, characterized in that: The method comprises modules or units for executing the method according to any one of claims 1 to 6.

21. A communication device, characterized in that: The method comprises a module or a unit for executing 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: Comprising the communication device as claimed in claim 20 and claim 21.

23. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program or instructions, which, when executed on a communication device, causes the communication device to execute 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 comprises a computer program or instructions for performing the method of any one of claims 1 to 6, or the method of any one of claims 7 to 16, or the method of 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 instructions stored in a memory through the communication interface to execute 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