Communication method and communication apparatus

Abstract

The present application provides a communication method and a communication apparatus. In the method, according to information feedback of second apparatuses (e.g., sub nodes) (e.g., feeding back training state information, data state information, etc. of the sub nodes), a first apparatus (e.g., a central node) can make better plan and schedule the second apparatuses to perform distributed training, thereby improving the efficiency of distributed training.

Description

Communication method and communication device

[0001] This application claims priority to the Chinese patent application with application number 202310721724.4 filed with the State Intellectual Property Office of China on June 16, 2023, and priority to the Chinese patent application with the invention name “A Communication Method and Communication Device”, all contents of which are incorporated by reference into this application. Technical Field

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

[0003] At present, relevant protocol standards have begun to discuss the standardization of artificial intelligence (AI). For example, to address the generalization problem of AI models, centralized AI model training methods and distributed AI model training methods can be used. Among them, centralized AI model training refers to the use of a large amount of information / data collected from multiple child nodes and stored in a central node to conduct centralized model training, so that the trained model can achieve good classification / inference effects. However, the centralized AI model training method also faces many problems: the scale of AI models tends to grow exponentially over time, the training complexity is too high, and the model training time and training convergence are difficult to meet the requirements; considering the limitations of user data privacy protection, centralized AI model training also faces problems such as difficulty in data acquisition and high data interaction overhead.

[0004] Unlike centralized AI model training methods, distributed AI model training does not require collecting and aggregating data from multiple child nodes to a central node for centralized training. Instead, each child node is first trained locally based on local data, and then the intermediate results obtained during training (such as model parameters or gradients, etc.) are transferred between the child nodes and the central node. Finally, the intermediate results obtained are fused at the central node to complete the training and update of the entire model. However, under the distributed AI learning architecture, communication resources / computing resources are limited, and the central node cannot obtain the training results of all child nodes in each iteration; during the merging process, the training results of some child nodes may be unsatisfactory, which ultimately affects the accuracy of model training or requires more communication rounds to complete the final model update. Therefore, how the central node can better plan and schedule child nodes for distributed training under the distributed AI learning architecture is a problem worth studying.

[0005] Summary of the Invention

[0006] The present application provides a communication method and a communication device, which can better plan and schedule sub-nodes for distributed training, thereby improving the efficiency of distributed training.

[0007] In the first aspect, the present application provides a communication method, which is performed by a first device. In a possible implementation, the first device can be a central node of a training network (such as a base station, a terminal, etc.), or a component of a central node (such as a processor, a chip, or a chip system, etc.), or a logic module that can realize all or part of the functions of a central node. Among them, the first device sends multiple first messages, and the multiple first messages are used to request multiple second devices to perform distributed training. The first device receives multiple second messages, and any second message among the multiple second messages includes one or more of the following information: training status information of the second device corresponding to the second message, data status information of the second device corresponding to the second message, and first indication information indicating whether the second device corresponding to the second message meets the training requirements. The first device schedules the second device participating in the distributed training based on the multiple second messages.

[0008] In this method, through the information feedback of the second device (such as the sub-node in the training network), the first device (such as the central node in the training network) can better plan and schedule the sub-nodes for distributed training, which is conducive to improving the efficiency of distributed training.

[0009] In a possible implementation, the first message includes second indication information, where the second indication information is used to indicate that the corresponding second device is requested to perform distributed training.

[0010] In this method, the first device can specifically instruct the corresponding (specified) second device to perform distributed training through the second indication information to obtain the training status information and / or data status information of the corresponding second device, which is conducive to the first device to better plan and schedule sub-nodes for distributed training.

[0011] In one possible implementation, the first message further includes one or more of the following information: currently trained full model parameters, currently trained sub-model parameters of the corresponding second device, and training round information. The training round information includes a first training round number for requesting the second device to perform a complete training or parameter update on all training samples, and / or a second training round number for requesting the second device to perform a complete training or parameter update on some training samples.

[0012] In this method, the first message sent by the first device to the second device can carry training-related parameters, so that the second device can feed back corresponding training data, which is conducive to improving the efficiency of distributed training.

[0013] In one possible implementation, the training status information of the second device corresponding to the second message includes convergence information obtained by the second device after training and updating the first training times and / or the second training times based on the training model at the current moment and the corresponding data; the convergence information includes cross-validation accuracy or cross-validation test error.

[0014] In one possible implementation, the first device schedules the corresponding second device to participate in the distributed training based on the training state information. For example, the first device may prioritize scheduling the second device with lower cross-validation accuracy to participate in the distributed training.

[0015] In the above method, the first device can schedule the corresponding second device to participate in distributed training based on the training status information (such as training model, convergence information obtained from training, etc.) specifically fed back by the second device (such as giving priority to scheduling the second device with lower cross-validation accuracy, the data of the second device has a greater demand for model updates, and the previous model may not have been traversed to the second device).

[0016] In one possible implementation, the data status information includes one or more of the following information: quality information of the data corresponding to the second device, environmental information of the second device, first characteristic information of the data corresponding to the second device, second characteristic information of the data corresponding to the second device, computing power information of the second device, and communication capability information of the second device. The quality information of the data corresponding to the second device includes one or more of the following information: the signal-to-noise ratio of the data corresponding to the second device, the signal-to-interference-and-noise ratio of the data corresponding to the second device, and the number of samples of the data corresponding to the second device. The environmental information of the second device includes the location information and / or environmental parameters of the second device. The first characteristic information of the data corresponding to the second device includes a first characteristic distribution of the data corresponding to the second device. The second characteristic information of the data corresponding to the second device includes a second characteristic distribution obtained by feature extraction of the data corresponding to the second device. The computing power information of the second device includes one or more of the following information: the computational latency of the second device, the number of operations that can be performed per unit time, and the number of multiplications / additions that can be performed per unit time. The communication capability information of the second device includes one or more of the following information: the communication latency of the second device, the channel quality indicator (CQI) corresponding to the second device, the rank indicator (RI) of the channel corresponding to the second device, and the reference signal received power (RSRP) of the channel corresponding to the second device.

[0017] In one possible implementation, the first device schedules the corresponding second device to participate in the distributed training based on the data status information. For example, the first device may prioritize scheduling the second device whose training samples differ / deviate significantly from those of the previous distributed training.

[0018] In the above method, the first device can schedule the corresponding second device to participate in distributed training based on the data status information specifically fed back by the second device (such as the difference / deviation degree between the first feature information and the training samples already available in the first device, or the training samples of the previous distributed training, etc.) (such as giving priority to scheduling the second device whose training samples have a larger difference / deviation degree from the previous distributed training, because the data of the second device has a greater demand for model updating, and the previous model may not have traversed the second device).

[0019] In one possible implementation, the first message also includes one or more of the following information: quality requirements for the data corresponding to the second device, environmental requirements for the second device, minimum computing power requirements for the second device, minimum communication capability requirements for the second device, first characteristic information requirements for the data corresponding to the second device, and second characteristic information requirements for the data corresponding to the second device.

[0020] In this method, the first device can also obtain information such as the minimum computing power and minimum communication capability requirements of the second device, so as to determine whether the second device meets the training requirements and whether to participate in the current distributed training. This is conducive to ensuring that the distributed training can obtain updated results within the specified time, meet the latency requirements, and ensure the completeness, accuracy, and contribution of the distributed training to the large model.

[0021] In one possible implementation, the first indication information includes confirmation indication information or rejection indication information. The confirmation indication information is used to indicate one or more of the following information: the quality information of the data corresponding to the second device meets the quality requirements, the environmental information of the second device meets the environmental requirements, the computing power of the second device meets the minimum computing power requirements, the communication capability information of the second device meets the minimum communication capability requirements, the first feature information of the data corresponding to the second device meets the first feature information requirements, and the second feature information of the data corresponding to the second device meets the second feature information requirements. The rejection indication information is used to indicate one or more of the following information: the quality information of the data corresponding to the second device does not meet the quality requirements, the environmental information of the second device does not meet the environmental requirements, the computing power of the second device does not meet the minimum computing power requirements, the communication capability information of the second device does not meet the minimum communication capability requirements, the first feature information of the data corresponding to the second device does not meet the first feature information requirements, and the second feature information of the data corresponding to the second device does not meet the second feature information requirements.

[0022] In one possible implementation, the first device schedules all or part of the second device whose first indication information is confirmation indication information to participate in distributed training; or, the first device schedules all or part of the second device whose first indication information is not rejection indication information or has not fed back rejection indication information to participate in distributed training.

[0023] In the above method, the first device can receive confirmation indication information or rejection indication information fed back by the second device and perform scheduling, which is conducive to reducing the communication and computing overhead of the sub-nodes, ensuring the completeness, accuracy, and contribution to the large model of distributed training.

[0024] In a possible implementation, the types of the training status information, the data status information, and the first indication information are different.

[0025] In an embodiment in which a first device schedules a second device to participate in distributed training according to multiple second messages, when the multiple second messages include at least two types of information, the second device to participate in the distributed training is scheduled according to the various types of information included in the multiple second messages and the weights of the various types of information.

[0026] In this method, if the information received by the first device includes one or more of training status information, data status information, and first indication information, the first device can schedule the corresponding second device based on the information and weights to ensure the completeness, accuracy, contribution to the large model, etc. of the distributed training.

[0027] In the second aspect, the present application provides a communication method, which is performed by a second device. In one possible implementation, the first device can be a sub-node of the training network (such as a base station, terminal, etc.), or a component of a sub-node (such as a processor, chip, or chip system, etc.), or a logic module that can realize all or part of the functions of the sub-node. Among them, the second device receives a first message, which is used to request the second device to perform distributed training. The second device sends a second message, which includes one or more of the following information: training status information of the second device, data status information of the second device, and first indication information indicating whether the second device meets the training requirements. The second device participates in distributed training according to the scheduling of the first device.

[0028] In this method, the second device can feed back training and / or data-related information to the first device, which is beneficial for the first device to better plan and schedule sub-nodes for distributed training, and is beneficial for improving the efficiency of distributed training.

[0029] In one possible implementation, the first message further includes one or more of the following information: currently trained full model parameters, currently trained sub-model parameters of the corresponding second device, and training round information. The training round information includes a first training round number for requesting the second device to perform a complete training or parameter update on all training samples, and / or a second training round number for requesting the second device to perform a complete training or parameter update on some training samples.

[0030] In this method, the first message received by the second device includes training-related parameters, so that the second device can feed back corresponding training data, which is beneficial to improving the efficiency of distributed training.

[0031] In one possible implementation, the training status information of the second device corresponding to the second message includes convergence information obtained by the second device after training and updating the first training times and / or the second training times based on the training model at the current moment and the corresponding data; the convergence information includes cross-validation accuracy or cross-validation test error.

[0032] In this method, the second device can feedback training status information (such as training model, convergence information obtained from training, etc.) to the first device, which is beneficial for the first device to schedule the corresponding second device to participate in distributed training according to the training status information (such as giving priority to scheduling the second device with lower cross-validation accuracy, the data of the second device has a greater demand for model updates, and the previous model may not have been traversed to the second device).

[0033] In one possible implementation, the data status information includes one or more of the following information: quality information of the data corresponding to the second device, environmental information of the second device, first characteristic information of the data corresponding to the second device, second characteristic information of the data corresponding to the second device, computing power information of the second device, and communication capability information of the second device. The quality information of the data corresponding to the second device includes one or more of the following information: the signal-to-noise ratio of the data corresponding to the second device, the signal-to-interference-and-noise ratio of the data corresponding to the second device, and the number of samples of the data corresponding to the second device. The environmental information of the second device includes the location information and / or environmental parameters of the second device. The first characteristic information of the data corresponding to the second device includes a first characteristic distribution of the data corresponding to the second device. The second characteristic information of the data corresponding to the second device includes a second characteristic distribution obtained by feature extraction of the data corresponding to the second device. The computing power information of the second device includes one or more of the following information: the computational latency of the second device, the number of operations that can be performed per unit time, and the number of multiplications / additions that can be performed per unit time. The communication capability information of the second device includes one or more of the following information: the communication latency of the second device, the channel quality indicator (CQI) corresponding to the second device, the rank indicator (RI) of the channel corresponding to the second device, and the reference signal received power (RSRP) of the channel corresponding to the second device.

[0034] In this method, the second device can feedback data status information to the first device (such as the difference / deviation degree from the first feature information and the training samples already available in the first device, or the training samples of the previous distributed training, etc.), which is conducive to the first device scheduling the corresponding second device to participate in the distributed training (such as giving priority to scheduling the second device whose training samples are more different / deviation from the previous distributed training, the data of the second device has a greater demand for model updates, and the previous model may not have traversed the second device).

[0035] In one possible implementation, the first message also includes one or more of the following information: quality requirements for the data corresponding to the second device, environmental requirements for the second device, minimum computing power requirements for the second device, minimum communication capability requirements for the second device, first characteristic information requirements for the data corresponding to the second device, and second characteristic information requirements for the data corresponding to the second device.

[0036] In this method, the second device can report the minimum computing power, minimum communication capability requirements and other information to the first device in advance, which is beneficial for the first device to determine whether the second device meets the training requirements and whether to participate in the current distributed training. It is beneficial to ensure that the distributed training can obtain updated results within the specified time, meet the latency requirements, and ensure the completeness, accuracy, and contribution of the distributed training to the large model.

[0037] In one possible implementation, the first indication information includes confirmation indication information or rejection indication information. The confirmation indication information is used to indicate one or more of the following information: the quality information of the data corresponding to the second device meets the quality requirements, the environmental information of the second device meets the environmental requirements, the computing power of the second device meets the minimum computing power requirements, the communication capability information of the second device meets the minimum communication capability requirements, the first feature information of the data corresponding to the second device meets the first feature information requirements, and the second feature information of the data corresponding to the second device meets the second feature information requirements. The rejection indication information is used to indicate one or more of the following information: the quality information of the data corresponding to the second device does not meet the quality requirements, the environmental information of the second device does not meet the environmental requirements, the computing power of the second device does not meet the minimum computing power requirements, the communication capability information of the second device does not meet the minimum communication capability requirements, the first feature information of the data corresponding to the second device does not meet the first feature information requirements, and the second feature information of the data corresponding to the second device does not meet the second feature information requirements.

[0038] In this method, the second device can determine whether to participate in the training based on the training request and feedback confirmation indication information or rejection indication information, which is conducive to reducing the communication and computing overhead of the sub-nodes, ensuring the completeness, accuracy, and contribution to the large model of distributed training.

[0039] In a third aspect, the present application provides a communication device. In one possible implementation, the communication device may be a central node of a training network, a device of a central node, or a device capable of being used in conjunction with a central node. In one possible implementation, the communication device may include a functional module, which may be implemented as a hardware circuit, software, or a combination of hardware circuits and software.

[0040] In one possible implementation, the communication device includes a communication unit and a processing unit. The communication unit is configured to send multiple first messages, each of which is used to request multiple second devices to perform distributed training. The communication unit is further configured to receive multiple second messages, wherein any one of the multiple second messages includes one or more of the following information: training status information of the second device corresponding to the second message, data status information of the second device corresponding to the second message, and first indication information indicating whether the second device corresponding to the second message meets training requirements. The processing unit is configured to schedule the second devices participating in the distributed training based on the multiple second messages.

[0041] In a possible implementation, the first message includes second indication information, where the second indication information is used to indicate that the corresponding second device is requested to perform distributed training.

[0042] In one possible implementation, the first message further includes one or more of the following information: currently trained full model parameters, currently trained sub-model parameters of the corresponding second device, and training round information. The training round information includes a first training round number for requesting the second device to perform a complete training or parameter update on all training samples, and / or a second training round number for requesting the second device to perform a complete training or parameter update on some training samples.

[0043] In one possible implementation, the training status information of the second device corresponding to the second message includes convergence information obtained by the second device after training and updating the first training times and / or the second training times based on the training model at the current moment and the corresponding data; the convergence information includes cross-validation accuracy or cross-validation test error.

[0044] In one possible embodiment, the processing unit is configured to schedule a second device to participate in distributed training based on the plurality of second messages, including: scheduling a corresponding second device to participate in distributed training based on the training state information. For example, the first device may prioritize scheduling a second device with a lower cross-validation accuracy to participate in distributed training.

[0045] In one possible implementation, the data status information includes one or more of the following information: quality information of the data corresponding to the second device, environmental information of the second device, first characteristic information of the data corresponding to the second device, second characteristic information of the data corresponding to the second device, computing power information of the second device, and communication capability information of the second device. The quality information of the data corresponding to the second device includes one or more of the following information: the signal-to-noise ratio of the data corresponding to the second device, the signal-to-interference-and-noise ratio of the data corresponding to the second device, and the number of samples of the data corresponding to the second device. The environmental information of the second device includes the location information and / or environmental parameters of the second device. The first characteristic information of the data corresponding to the second device includes a first characteristic distribution of the data corresponding to the second device. The second characteristic information of the data corresponding to the second device includes a second characteristic distribution obtained by feature extraction of the data corresponding to the second device. The computing power information of the second device includes one or more of the following information: the computing latency of the second device, the number of operations that can be performed per unit time, and the number of multiplications / additions that can be performed per unit time. The communication capability information of the second device includes one or more of the following information: the communication latency of the second device, the channel quality indicator (CQI) corresponding to the second device, the rank indicator (RI) of the channel corresponding to the second device, and the reference signal received power (RSRP) of the channel corresponding to the second device.

[0046] In one possible embodiment, the processing unit is configured to schedule a second device to participate in distributed training based on the plurality of second messages, including scheduling the corresponding second device to participate in distributed training based on the data state information. For example, the first device may prioritize scheduling a second device whose training samples differ significantly from / deviate from a previous distributed training session.

[0047] In one possible implementation, the first message also includes one or more of the following information: quality requirements for the data corresponding to the second device, environmental requirements for the second device, minimum computing power requirements for the second device, minimum communication capability requirements for the second device, first characteristic information requirements for the data corresponding to the second device, and second characteristic information requirements for the data corresponding to the second device.

[0048] In one possible implementation, the first indication information includes confirmation indication information or rejection indication information. The confirmation indication information is used to indicate one or more of the following information: the quality information of the data corresponding to the second device meets the quality requirements, the environmental information of the second device meets the environmental requirements, the computing power of the second device meets the minimum computing power requirements, the communication capability information of the second device meets the minimum communication capability requirements, the first feature information of the data corresponding to the second device meets the first feature information requirements, and the second feature information of the data corresponding to the second device meets the second feature information requirements. The rejection indication information is used to indicate one or more of the following information: the quality information of the data corresponding to the second device does not meet the quality requirements, the environmental information of the second device does not meet the environmental requirements, the computing power of the second device does not meet the minimum computing power requirements, the communication capability information of the second device does not meet the minimum communication capability requirements, the first feature information of the data corresponding to the second device does not meet the first feature information requirements, and the second feature information of the data corresponding to the second device does not meet the second feature information requirements.

[0049] In one possible embodiment, the processing unit is used to schedule the second device to participate in the distributed training based on multiple second messages, including: scheduling all or part of the second devices whose first indication information is confirmation indication information to participate in the distributed training; or scheduling all or part of the second devices whose first indication information is not rejection indication information or has not fed back rejection indication information to participate in the distributed training.

[0050] In a possible implementation, the types of the training state information, the data state information, and the first indication information are different.

[0051] In an embodiment in which the processing unit schedules the second device participating in the distributed training according to multiple second messages, when the multiple second messages include at least two types of information, the processing unit schedules the second device participating in the distributed training according to the various types of information included in the multiple second messages and the weights of the various types of information.

[0052] In a fourth aspect, the present application provides a communication device. In one possible implementation, the communication device may be a central node of a training network, a device of a central node, or a device capable of being used in conjunction with a central node. In one possible implementation, the communication device may include a functional module, which may be implemented as a hardware circuit, software, or a combination of hardware circuit and software.

[0053] In one possible implementation, the communication device includes a communication unit and a processing unit. The communication unit receives a first message requesting a second device to perform distributed training. The communication unit is further configured to send a second message including one or more of the following: training status information of the second device, data status information of the second device, and first indication information indicating whether the second device meets training requirements. The processing unit is configured to participate in the distributed training according to the first device's schedule.

[0054] In one possible implementation, the first message further includes one or more of the following information: currently trained full model parameters, currently trained sub-model parameters of the corresponding second device, and training round information. The training round information includes a first training round number for requesting the second device to perform a complete training or parameter update on all training samples, and / or a second training round number for requesting the second device to perform a complete training or parameter update on some training samples.

[0055] In one possible implementation, the training status information of the second device corresponding to the second message includes convergence information obtained by the second device after training and updating the first training times and / or the second training times based on the training model at the current moment and the corresponding data; the convergence information includes cross-validation accuracy or cross-validation test error.

[0056] In one possible implementation, the data status information includes one or more of the following information: quality information of the data corresponding to the second device, environmental information of the second device, first characteristic information of the data corresponding to the second device, second characteristic information of the data corresponding to the second device, computing power information of the second device, and communication capability information of the second device. The quality information of the data corresponding to the second device includes one or more of the following information: the signal-to-noise ratio of the data corresponding to the second device, the signal-to-interference-and-noise ratio of the data corresponding to the second device, and the number of samples of the data corresponding to the second device. The environmental information of the second device includes the location information and / or environmental parameters of the second device. The first characteristic information of the data corresponding to the second device includes a first characteristic distribution of the data corresponding to the second device. The second characteristic information of the data corresponding to the second device includes a second characteristic distribution obtained by feature extraction of the data corresponding to the second device. The computing power information of the second device includes one or more of the following information: the computational latency of the second device, the number of operations that can be performed per unit time, and the number of multiplications / additions that can be performed per unit time. The communication capability information of the second device includes one or more of the following information: the communication latency of the second device, the channel quality indicator (CQI) corresponding to the second device, the rank indicator (RI) of the channel corresponding to the second device, and the reference signal received power (RSRP) of the channel corresponding to the second device.

[0057] In one possible implementation, the first message also includes one or more of the following information: quality requirements for the data corresponding to the second device, environmental requirements for the second device, minimum computing power requirements for the second device, minimum communication capability requirements for the second device, first characteristic information requirements for the data corresponding to the second device, and second characteristic information requirements for the data corresponding to the second device.

[0058] In one possible implementation, the first indication information includes confirmation indication information or rejection indication information. The confirmation indication information is used to indicate one or more of the following information: the quality information of the data corresponding to the second device meets the quality requirements, the environmental information of the second device meets the environmental requirements, the computing power of the second device meets the minimum computing power requirements, the communication capability information of the second device meets the minimum communication capability requirements, the first feature information of the data corresponding to the second device meets the first feature information requirements, and the second feature information of the data corresponding to the second device meets the second feature information requirements. The rejection indication information is used to indicate one or more of the following information: the quality information of the data corresponding to the second device does not meet the quality requirements, the environmental information of the second device does not meet the environmental requirements, the computing power of the second device does not meet the minimum computing power requirements, the communication capability information of the second device does not meet the minimum communication capability requirements, the first feature information of the data corresponding to the second device does not meet the first feature information requirements, and the second feature information of the data corresponding to the second device does not meet the second feature information requirements.

[0059] In a fifth aspect, the present application provides a communication device, comprising: a processor configured to execute instructions; optionally, the communication device further comprising a memory configured to store the instructions, wherein when the instructions are executed by the processor, the communication device implements the method of the first aspect and any possible implementation of the first aspect. Optionally, the processor and the memory are coupled.

[0060] In a sixth aspect, the present application provides a communication device, comprising: a processor configured to execute instructions; optionally, the communication device further comprising a memory configured to store the instructions, wherein when the instructions are executed by the processor, the communication device implements the method of the second aspect and any possible implementation of the second aspect. Optionally, the processor and the memory are coupled.

[0061] In the seventh aspect, the present application provides a communication system, which includes multiple devices or equipment in the above-mentioned third to sixth aspects, so that the devices or equipment execute the methods in the first and second aspects, as well as any possible implementation of the first and second aspects.

[0062] In an eighth aspect, the present application provides a computer-readable storage medium storing instructions, which, when the instructions are executed on a computer, enable the computer to execute the method of the first aspect and the second aspect, as well as any possible implementation of the first aspect and the second aspect.

[0063] In a ninth aspect, the present application provides a chip system comprising a processor and an interface, and optionally, a memory, for implementing the methods of the first and second aspects, as well as any possible implementation of the first and second aspects. The chip system may be composed solely of a chip, or may include a chip and other discrete components.

[0064] In a tenth aspect, the present application provides a computer program product comprising instructions, which, when executed on a computer, enable the computer to execute the method of the first aspect and the second aspect, as well as any possible implementation of the first aspect and the second aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] FIG1 is a schematic diagram of a communication system provided by this application;

[0066] FIG2 is a flow chart of a communication method provided by the present application;

[0067] FIG3 is a schematic diagram of a process of a first device scheduling a corresponding second device to perform distributed training according to training status information provided by the present application;

[0068] FIG4 is a schematic diagram of a process of a first device scheduling a corresponding second device to perform distributed training according to data status information provided by the present application;

[0069] FIG5 is a schematic diagram of a process of a first device scheduling a corresponding second device to perform distributed training according to first instruction information provided by the present application;

[0070] FIG6 is a schematic diagram of a communication device provided by the present application;

[0071] FIG7 is a schematic diagram of another communication device provided in this application. DETAILED DESCRIPTION

[0072] In the embodiments of this application, " / " can indicate that the associated objects are in an "or" relationship. For example, A / B can mean A or B. "And / or" can be used to describe the existence of three relationships between associated objects. For example, "A and / or B" can mean: A exists alone, A and B exists simultaneously, or B exists alone. A and B can be singular or plural. To facilitate the description of the technical solutions of the embodiments of this application, the words "first" and "second" may be used in the embodiments of this application to distinguish between technical features with the same or similar functions. The words "first" and "second" do not limit the number or order of execution, and the words "first" and "second" do not necessarily mean different. In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. The use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner for easier understanding.

[0073] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0074] In order to solve the problem of how the central node can better plan and schedule sub-nodes for distributed training under the architecture of distributed AI learning, the present application provides a communication method and a communication device, which can selectively schedule sub-nodes for distributed training, which is conducive to improving the efficiency of distributed training.

[0075] Among them, the communication method provided in the present application can be applied to the communication system shown in Figure 1, for example, the communication system includes a central node and a sub-node. Among them, the central node can be an access network device (including a base station, a macro base station, a micro base station, etc.), a terminal device, etc., and the sub-node can be an access network device (including a base station, a macro base station, a micro base station, etc.), a terminal device, etc. Optionally, the communication method is applicable to 4G, 5G or future mobile communication systems. The communication method is applicable to low-frequency scenarios (sub 6G) and also to high-frequency scenarios (above 6G). The communication method is applicable to single transmit receive point (Single-TRP) or multiple transmit receive point (Multi-TRP) scenarios, as well as any derived scenarios thereof. The communication method is applicable to new radio (NR) uplink transmission.

[0076] Among them, terminal devices, also known as user equipment (UE), mobile station (MS), mobile terminal (MT), etc., refer to devices that provide voice and / or data connectivity to users. For example, handheld devices and in-vehicle devices with wireless connection capabilities. Currently, some examples of terminal devices include: mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices, drones, 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, terminal devices in 5G networks, terminal devices in future evolved PLMN networks, or terminal devices in future communication systems.

[0077] The access network device refers to a radio access network (RAN) node (or device) that connects a terminal device to a wireless network, and may also be referred to as a base station. For example, some examples of RAN nodes include: a gNB, a transmission reception point (TRP), an evolved Node B (eNB), a radio network controller (RNC), a Node B (NB), a base station controller (BSC), a base transceiver station (BTS), a home base station (e.g., a home evolved NodeB, or a home Node B, HNB), a base band unit (BBU), or a wireless fidelity (Wifi) access point (AP), a satellite in a satellite communication system, a radio controller in a cloud radio access network (CRAN) scenario, a wearable device, a drone, or a device in an Internet of Vehicles (e.g., vehicle to everything (V2X)), or a communication device in device to device (D2D) communication. In addition, in a network structure, the access network device may include a centralized unit (CU) node, a distributed unit (DU) node, or a RAN device including a CU node and a DU node. The RAN device including the CU node and the DU node splits the protocol layer of the eNB in ​​the long term evolution (LTE) system, places the functions of some protocol layers in the CU for centralized control, and distributes the functions of the remaining part or all of the protocol layers in the DU, which is centrally controlled by the CU. In some deployments of the access network device, the CU can also be divided into a CU-control plane (CP) and a CU-user plane (UP), etc. In other deployments of the access network device, the access network device can also be an antenna unit (RU), etc. In some other deployments of the access network device, the access network device can also be an open radio access network (ORAN) architecture, etc. This application does not limit the specific type of the access network device.For example, when the access network device is an ORAN architecture, the access network device shown in the embodiment of the present application may be an access network device in the ORAN, or a module in the access network device. In the ORAN system, CU may also be referred to as open (O)-CU, DU may also be referred to as O-DU, CU-DU may also be referred to as O-CU-DU, CU-UP may also be referred to as O-CU-UP, and RU may also be referred to as O-RU.

[0078] It should be noted that:

[0079] "Sending" and "receiving" in the embodiments of the present application indicate the direction of signal transmission. For example, "sending configuration information to a terminal device" can be understood as the destination end of the configuration information being the terminal device, which can include direct sending through the air interface, and also includes indirect sending through the air interface by other units or modules. "Receiving configuration information from a network device" can be understood as the source end of the configuration information being the network device, which can include direct receiving from the network device through the air interface, and also includes indirect receiving from the network device through the air interface from other units or modules. "Sending" can also be understood as the "output" of the chip interface, and "receiving" can also be understood as the "input" of the chip interface.

[0080] In other words, sending and receiving can be performed between devices, for example, between a network device and a terminal device, or can be performed within a device, for example, sending or receiving between components, modules, chips, software modules or hardware modules within the device through a bus, wiring or interface.

[0081] It is understandable that information may be processed between the source and destination of information transmission, such as coding, modulation, etc., but the destination can understand the valid information from the source. Similar expressions in this application can be understood similarly and will not be repeated.

[0082] In the embodiments of the present application, "indication" may include direct indication and indirect indication, and may also include explicit indication and implicit indication. The information indicated by a certain information (such as the indication information described below) is called information to be indicated. In the specific implementation process, there are many ways to indicate the information to be indicated, such as but not limited to, the information to be indicated can be directly indicated, such as the information to be indicated itself or the index of the information to be indicated. The information to be indicated can also be indirectly indicated by indicating other information, wherein there is an association between the other information and the information to be indicated; it is also possible to indicate only a part of the information to be indicated, while the other parts of the information to be indicated are known or agreed in advance, for example, the indication of specific information can be achieved with the help of the arrangement order of each information agreed in advance (such as predefined by the protocol), thereby reducing the indication overhead to a certain extent. The present application does not limit the specific method of indication. It is understandable that, for the sender of the indication information, the indication information can be used to indicate the information to be indicated, and for the receiver of the indication information, the indication information can be used to determine the information to be indicated.

[0083] 1. To facilitate understanding, the definitions of relevant terms involved in this application are introduced in detail below.

[0084] 1. Artificial Intelligence: Giving machines human intelligence and applying computer hardware and software to simulate certain intelligent human behaviors, including machine learning and many other methods.

[0085] 2. Machine Learning: Learning models or rules from raw data. There are many different machine learning methods, such as neural networks, decision trees, support vector machines, etc.

[0086] 3. AI model: A function model that maps input of a certain dimension to output of a certain dimension, whose model parameters are obtained through machine learning training. For example, f(x) = ax 2 +b is a quadratic function model, which can be regarded as an AI model. a and b correspond to the parameters of the model and can be obtained through machine learning training.

[0087] 4. Neural network: For example, artificial neural network, which is a mathematical model that imitates the behavioral characteristics of animal neural networks and performs distributed parallel information processing. It is a special form of AI model.

[0088] 5. Dataset: Data used for model training, verification, and testing in machine learning. The quantity and quality of data will affect the effectiveness of machine learning.

[0089] 6. Model training: By selecting a suitable loss function and applying an optimization algorithm to train the model parameters, the loss function value is minimized.

[0090] 7. Loss function: used to measure the difference between the model's predicted value and the true value.

[0091] 8. Model testing: After training, apply test data to evaluate model performance.

[0092] 9. Model application: Apply the trained model to solve practical problems.

[0093] 10. Supervised Learning: Based on collected sample values ​​and sample labels, a machine learning algorithm is applied to learn the mapping relationship from sample values ​​to sample labels. This learned mapping relationship is then expressed using a machine learning model. The process of training a machine learning model is the process of learning this mapping relationship. For example, in signal detection, a noisy received signal is a sample, and the true constellation point corresponding to this signal is the label. Through training, machine learning aims to learn the mapping relationship between samples and labels, that is, to enable the machine learning model to learn a signal detector. During training, the model parameters are optimized by calculating the error between the model's predicted value and the true label. Once the mapping relationship is learned, it can be applied to predict the sample label for each new sample. The mapping relationship learned by supervised learning can include linear mappings and nonlinear mappings. The learning task can be divided into classification and regression tasks based on the type of label.

[0094] 11. Federated Learning: Federated learning is a machine learning framework designed to effectively enable multiple organizations to utilize data and conduct machine learning modeling while ensuring user privacy and data security. Within the federated learning framework, nodes communicate not with the data itself but with intermediate results from training, such as model parameters or gradients. The classic federated learning system architecture may include a central node and multiple distributed nodes. These distributed nodes are all connected to the central node, and each node contains a distributed dataset specific to its application environment. As a distributed machine learning paradigm, federated learning can effectively address the data silo problem, enabling participants to jointly model without sharing data. This technically breaks down data silos and enables AI collaboration. Depending on the distribution of data sources among the participating parties, federated learning can be categorized into three types: horizontal federated learning, vertical federated learning, and federated transfer learning.

[0095] Horizontal federated learning refers to splitting the dataset horizontally (i.e., the user dimension) when there is a lot of overlap in user features but little overlap in users between two datasets, and taking out the data with the same user features but different users for training. Vertical federated learning refers to splitting the dataset vertically (i.e., the feature dimension) when there is a lot of overlap in users but little overlap in user features between two datasets, and taking out the data with the same users but different user features for training. Federated transfer learning refers to not splitting the data when there is little overlap in users and user features between two datasets, and applying transfer learning to overcome insufficient data or labels.

[0096] 12. Centralized AI model training:

[0097] Centralized AI model training involves using a large amount of information / data collected from multiple sub-nodes and stored in a central node to conduct centralized model training, enabling the trained model to achieve good classification / inference results. AI models trained through centralized training have good generalization capabilities and performance due to the characteristics of extensive data. However, centralized AI model training methods also face many problems:

[0098] (1) The scale of AI models is growing exponentially over time (for example, the largest model currently has more than 100 billion model parameters). Centralized AI model training faces the problem of excessive training complexity, and model training time and training convergence are difficult to meet requirements;

[0099] (2) Considering the limitations of user data privacy protection, centralized AI model training also faces problems such as difficulty in data acquisition and high data interaction overhead.

[0100] 13. Distributed AI model training: In distributed AI model training, the workload for training the model can be split and shared across multiple microprocessors, called sub-nodes. These sub-nodes can work in parallel to accelerate model training. Federated learning is a typical distributed AI model training framework.

[0101] Unlike centralized AI model training methods, distributed AI model training does not require data to be collected and aggregated from multiple child nodes to a central node for centralized training. Instead, each child node first performs local training based on its own data. Intermediate training results (such as model parameters or gradients) are then transferred between the child nodes and the central node. Finally, the central node fuses these intermediate results to complete full model training and update. Compared to centralized AI model training, distributed AI model training requires only that each child node (or some of them) transfer intermediate training results, effectively reducing the air interface overhead of transmitting data from child nodes to the central node. Furthermore, by fully learning the local data characteristics of each child node, distributed AI models can effectively approach the performance of centralized AI models. Therefore, in wireless communication systems, researching and developing distributed AI model training technology is an important technical means to effectively enable network intelligence. However, due to limited communication and computing resources, the central node cannot obtain the training results of all child nodes in each iteration. Furthermore, during the fusion of intermediate results, some child nodes may receive suboptimal training results, resulting in poor data quality and ultimately affecting the accuracy of model training.

[0102] 14. Batch size: Indicates the number of samples participating in training in one training.

[0103] 15. Epoch: During AI training, an epoch represents a complete training run for the samples specified by the batch-size. Generally, training requires at least one epoch.

[0104] 2. Communication method provided by this application:

[0105] FIG2 is a flow chart of a communication method provided by the present application. The communication method is applied to the communication system shown in FIG1. ​​For example, the communication method can be implemented by interaction between a first device (such as a central node) and a second device (such as a sub-node), including the following steps:

[0106] S101: A first device sends multiple first messages to multiple second devices. Correspondingly, the multiple second devices receive the first messages respectively.

[0107] The multiple first messages are used to request multiple second devices to perform distributed training. For example, assuming that the distributed training network includes a central node and multiple child nodes (e.g., child node 1 and child node 2), the central node can send a first message to each of the multiple child nodes, each first message being used to request the corresponding child node to perform distributed training.

[0108] In one possible implementation, the first message is a distributed training request message. The first message includes second indication information, and the second indication information is used to instruct the corresponding second device to perform distributed training. For example, the central node sends distributed training request message 1 to child node 1. The distributed training request message 1 includes second indication information, which is used to instruct the child node 1 to perform distributed training.

[0109] Optionally, the first message may also carry training requirements. For example, each second device may correspond to different training requirements, and the training requirements of each second device may include one or more of the following information: quality requirements for the data corresponding to the second device, environmental requirements for the second device, minimum computing power requirements for the second device, minimum communication capability requirements for the second device, first feature information requirements for the data corresponding to the second device, second feature information requirements for the data corresponding to the second device, etc.

[0110] S102: Multiple second devices send multiple second messages to a first device. Correspondingly, the first device receives multiple second messages from the multiple second devices.

[0111] Among them, any second message among the multiple second messages includes one or more of the following information: training status information of the second device corresponding to the second message, data status information of the second device corresponding to the second message, and first indication information indicating whether the second device corresponding to the second message meets the training requirements.

[0112] The training status information of the second device corresponding to the second message refers to the information obtained by the second device during preliminary training, including but not limited to the following information: convergence information obtained by the second device after a first training update based on the current training model and the corresponding data, convergence information obtained by the second device after a second training update based on the current training model and the corresponding data, etc. Convergence information includes cross-validation accuracy or cross-validation test error, etc. The first training number refers to the number of epochs in which all training samples are fully trained or the number of parameter updates is a preset fixed number, or the first training number is a preset fixed number; the second training number refers to the number of iterations in which part of the training samples are fully trained or the number of parameter updates is a preset fixed number. For example, assuming that the second device corresponding to the second message is child node 1, the training status information fed back by child node 1 may include the cross-validation accuracy / cross-validation test error obtained by child node 1 after a first training update based on the current training model and the corresponding data, and the cross-validation accuracy / cross-validation test error obtained by child node 1 after a second training update based on the current training model and the corresponding data.

[0113] The data status information of the second device corresponding to the second message refers to the current data status of the second device, that is, the second device directly feeds back the current data status without training, including one or more of the following information: quality information of the data corresponding to the second device, environmental information of the second device, first feature information of the data corresponding to the second device, second feature information of the data corresponding to the second device, computing power information of the second device, and communication capability information of the second device.

[0114] The quality information of the data corresponding to the second device includes one or more of the following information: a signal-to-noise ratio (SNR) of the data corresponding to the second device, a signal-to-interference plus noise ratio (SINR) of the data corresponding to the second device, a number of samples of the data corresponding to the second device, and other information. For example, assuming that the second device corresponding to the second message is child node 1, the quality information of the data fed back by child node 1 may include the SNR / SINR of the data of child node 1, the number of sample points / batch number / batch-size of the data, and other information.

[0115] The environmental information of the second device includes location information and / or environmental parameters of the second device. For example, the location information of the second device may be geographic location information (e.g., three-dimensional coordinates) and a location identifier of a child node. The environmental parameters of the second device may be a channel state information (CSI) environment map, indicating the specific environment (e.g., urban environment or suburban environment) in which the second device is located.

[0116] The first characteristic information of the data corresponding to the second device includes a first characteristic distribution of the data corresponding to the second device. For example, assuming that the data corresponding to the second device is CSI, the first characteristic distribution may be a delay distribution, a beam distribution, a K-factor, etc. The delay distribution may be represented by the delay spread of the channel corresponding to the child node. The delay spread (DS) is an indicator of the multipath information / frequency selectivity of the feedback channel.

[0117] The second feature information of the data corresponding to the second device includes a second feature distribution obtained by feature extraction of the data corresponding to the second device. For example, the second device can perform feature extraction on the channel data, thereby converting the channel data into parameters of another domain (such as a binary domain).

[0118] The computing power information of the second device includes one or more of the following information: the computing latency of the second device, the number of operations that can be performed per unit time, the number of multiplications / additions that can be performed per unit time, and other information. For example, a child node may determine the computing latency of the child node based on the number of operations that can be performed per unit time, the amount of data, and the model scale.

[0119] The communication capability information of the second device includes one or more of the following information: the communication delay of the second device, the channel quality indicator (CQI), rank indication (RI), and reference signal received power (RSRP) corresponding to the second device. For example, the child node can obtain the CQI information, RI information, RSRP information, etc. of the child node based on the downlink reference signal. The computing power information and communication capability information of the second device can ensure that the central node obtains the required model update within the specified time limit.

[0120] Among them, the first indication information is used to indicate whether the second device corresponding to the second message meets the training requirements. For example, the child node can evaluate whether the training requirements are met based on the distributed training request message and the data of the child node. If it is met, the first indication information fed back by the child node can be confirmation indication information (such as confirmation (ACK)), indicating that the child node meets the training requirements; if it is not met, the first indication information fed back by the child node can be rejection indication information (such as non-acknowledge (NACK)), indicating that the child node does not meet the training requirements.

[0121] S103: The first device schedules the second device to participate in the distributed training according to the multiple second messages.

[0122] Among them, according to the different types of specific information carried in the second message, the first device can schedule the second device to participate in the distributed training based on different types of information. For example, the types of the training status information of the second device, the data status information of the second device, and the first indication information of the second device are different; when the second message includes the training status information of the second device (such as the cross-validation accuracy / cross-validation test error obtained by the second device based on the training model at the current moment and the corresponding data after the first training times), the first device can prioritize scheduling the second device with lower cross-validation accuracy / larger cross-validation test error to participate in the distributed training based on the cross-validation accuracy / cross-validation test error.

[0123] In one possible implementation, assuming that the second message carries at least two types of information, such as training status information and data status information of the second device, the first device can comprehensively consider these two types of information to schedule the corresponding second device to participate in distributed training. For example, when multiple second messages include at least two types of information, the first device can schedule the second device to participate in distributed training based on the various types of information included in the multiple second messages and the weights of the various types of information. Specifically, the central node can schedule the corresponding child node to participate in distributed training based on the training status information and the first weight of the training status information, as well as the data status information and the second weight of the data status information.

[0124] In this embodiment, through the information feedback from the second device (such as feedback of the training status information and data status information of the second device), the first device can better plan and schedule the sub-nodes for distributed training, which is conducive to improving the efficiency of distributed training.

[0125] 3. The specific process of the communication method described above is described in detail below.

[0126] The following examples take a distributed training network scenario as an example, assuming that the distributed training network scenario includes a first device (such as a central node) and multiple second devices (such as sub-nodes 1 to X).

[0127] 1. Example 1: The first device makes a scheduling decision based on the training status information fed back by the second device.

[0128] For example, FIG3 is a flow chart of a first device scheduling a corresponding second device to perform distributed training according to training state information provided by the present application, including the following steps:

[0129] S201: A first device sends multiple distributed training request messages to multiple second devices.

[0130] Among them, any distributed training request message among the multiple distributed training request messages includes but is not limited to the following information: second indication information indicating that the corresponding second device is requested to perform distributed training, full model parameters that have been trained at the current moment, sub-model parameters of the corresponding second device that have been trained at the current moment, training round information, etc. Among them, the training round information includes the first training number and / or the second training number. The first training number refers to the epoch in which all training samples are fully trained or the parameter is updated once, or the first training number is a preset fixed number; the second training number refers to the iteration number in which part of the training samples are fully trained or the parameter is updated once, or the second training number is a preset fixed number.

[0131] For example, the central node sends a distributed training request message to the child node X, which includes: the second indication information indicating that the child node X is requested to perform distributed training, the full model parameters trained at the current moment, the sub-model parameters of the child node X trained at the current moment, the first training number of P epochs for the child node X, and the second training number of P iterations for the child node X.

[0132] Optionally, the first device may send multiple distributed training request messages to multiple second devices by unicast (e.g., a central node sends point-to-point messages to each child node); or may send them by broadcast / multicast, thereby reducing transmission overhead (compared to unicast, transmission overhead can be reduced). Optionally, the distributed training request message may also be delivered in the form of a bitmap. For example, the first device may broadcast an X-bit message, where the Nth bit in the message is 1, indicating that a distributed training request is issued to child node N, and 0, indicating that a distributed training request is not issued to child node N.

[0133] S202, multiple second devices perform preliminary training according to their respective distributed training request messages and their respective data to obtain their respective training status information.

[0134] For example, child node X performs preliminary training based on the distributed training request message (e.g., including the full model parameters trained at the current moment, the sub-model parameters of child node X trained at the current moment, etc.) and the data at child node X, and obtains training status information of child node X (e.g., including the cross-validation accuracy or cross-validation test error of child node X after P epochs, the cross-validation accuracy or cross-validation test error of child node X after P iterations, etc.).

[0135] S203: The multiple second devices send training status information of the multiple second devices to the first device.

[0136] For example, the child nodes 1 to X respectively send their own training state information (eg, including training state information 1 to X) to the central node.

[0137] S204: The first device determines a second device that participates in the distributed training based on the training status information of the plurality of second devices.

[0138] For example, the central node evaluates the priority order of the cross-validation test errors of child nodes 1 to X (for example, a larger cross-validation test error indicates that the data of the child node has a greater demand for model update and has a higher priority for participating in scheduling; a smaller cross-validation test error indicates that the priority for participating in scheduling is lower) to determine the child nodes participating in distributed training.

[0139] Optionally, after S204, the following steps are further included:

[0140] S205: The first device sends a scheduling request message to the second device participating in the distributed training.

[0141] For example, the central node can send a scheduling request message to the child nodes participating in the distributed training in a point-to-point manner. The scheduling request message is used to request the corresponding child nodes to update the model and information.

[0142] For another example, the central node can broadcast / multicast a scheduling request message to all child nodes and transmit the scheduling information in the form of a bitmap; wherein, 0 in the bitmap indicates that the corresponding child node does not participate in this distributed training, and 1 indicates that the corresponding child node participates in this distributed training.

[0143] 2. Example 2: The first device makes a scheduling decision based on the data status information fed back by the second device.

[0144] For example, FIG4 is a flow chart of a first device scheduling a corresponding second device to perform distributed training according to data status information provided by the present application, including the following steps:

[0145] S301: A first device sends multiple distributed training request messages to multiple second devices.

[0146] Among them, the specific implementation of S301 can refer to the corresponding description in the previous S101 and S201. For example, the central node sends a distributed training request message to the child node X, and the distributed training request message includes: second indication information instructing the child node X to perform distributed training.

[0147] Optionally, since the second device in this embodiment may not perform training immediately after receiving the distributed training request message, the distributed training request message in this embodiment differs from the description in S201 in that it does not carry information such as the currently trained full model parameters, the currently trained sub-model parameters of child node X, the number of first training times requested for child node X, P epochs, and the number of second training times requested for child node X, P iterations. It can be understood that this embodiment reduces training latency compared to Example 1.

[0148] Optionally, the first device may send multiple distributed training request messages to multiple second devices by unicast (such as a central node sending point-to-point to each child node); or it may send by broadcast / multicast, thereby reducing transmission overhead (compared to unicast, transmission overhead can be reduced). Optionally, the distributed training request message may also be delivered in the form of a bitmap. For example, the first device may broadcast an X-bit message, in which the Nth bit of the message is 1, indicating that a distributed training request is issued to child node N, and 0, indicating that a distributed training request is not issued to child node N.

[0149] S302: The plurality of second devices send data status information of the plurality of second devices to the first device.

[0150] Among them, the specific description of the data status information of the second device can refer to the corresponding description in the previous S102. For example, subnode X sends the data status information of subnode X to the central node. The data status information of subnode X includes one or more of the following information: quality information of the data of subnode X, environmental information of subnode X, first feature information of subnode X, second feature information of subnode X, computing power information of subnode X, communication capability information of subnode X, etc.

[0151] In one possible implementation, the second device may feedback specific data status information to the first device in a predefined table or grid format. Assuming that the second device sets the number of bits for reporting data status information to K, the second device may divide the data status into 2 k Groups, each group of data status corresponds to K bits of data status information.

[0152] For example, Table 1 is a table of delay spreads of channels corresponding to a subnode and corresponding data status information. In Table 1, if K=2, the second device can divide the delay spreads of the channels corresponding to the subnodes into 4 groups, and each group of delay spreads corresponds to 2 bits of data status information.

[0153] Table 1: Delay spread of the channel corresponding to the child node and the corresponding data status information

[0154] According to Table 1, when the delay spread of the channel corresponding to the child node X satisfies the requirement of less than 100 ns, the data status information fed back by the child node X to the central node is 00.

[0155] For another example, Table 2 is a table of computation delay / communication delay and corresponding data status information. In Table 2, if K=2, the second device can divide the computation delay / communication delay of the subnode into 4 groups, and each group of delay extension corresponds to 2 bits of data status information.

[0156] Table 2: Computational delay / communication delay and corresponding data status information

[0157] According to Table 2, when the computation delay / communication delay of child node X satisfies the requirement of greater than 100 ms, the data status information fed back by child node X to the central node is 11.

[0158] S303: The first device determines a second device that participates in the distributed training based on data status information of the plurality of second devices.

[0159] For example, the central node evaluates the subnodes 1 to X and determines the subnodes that participate in the distributed training. Assuming that the communication delay is less than 100ms to meet the training requirements, the first device can schedule according to the delay feedback from the subnodes 1 to X (such as scheduling the subnodes that meet the delay requirement of less than 100ms). For another example, assuming that the delay spread of the channel corresponding to the subnode is greater than 200ns to meet the training requirements, the first device can schedule according to the delay spread feedback from the subnodes 1 to X (such as scheduling the subnodes that meet the delay spread greater than 200ns).

[0160] Optionally, after S303, the following steps are further included:

[0161] S304: The first device sends a scheduling request message to the second device participating in the distributed training.

[0162] The specific implementation of S304 can refer to the corresponding description in S205 and will not be repeated here.

[0163] 3. Example 3: The child node determines whether to perform distributed training based on the training request.

[0164] For example, FIG5 is a flowchart of a first device scheduling a corresponding second device to perform distributed training according to first indication information provided by the present application, including the following steps:

[0165] S401: A first device sends multiple distributed training request messages to multiple second devices.

[0166] Among them, the distributed training request message includes one or more of the following information: second indication information, quality requirements of the data corresponding to the second device, environmental requirements of the second device, minimum computing power requirements of the second device, minimum communication capability requirements of the second device, first characteristic information requirements of the data corresponding to the second device, and second characteristic information requirements of the data corresponding to the second device.

[0167] For example, the quality requirements of the data corresponding to the second device are related to the quality information of the data, including but not limited to: SNR / SINR / sample number thresholds, etc. The environmental requirements of the second device are related to the environmental information, including but not limited to: a specified location area and / or a specified CSI environment map, etc. The minimum computing power requirements of the second device are related to the computing power information, including but not limited to a calculation delay threshold, a threshold for the number of operations that can be executed per unit time, a threshold for the number of multiplications / additions that can be executed per unit time, etc. The minimum communication capability requirements of the second device are related to the communication capability information, including but not limited to: a communication delay threshold, a specified CQI, etc. The first characteristic information requirements of the second device are related to the first characteristic information, including a specified first characteristic distribution (such as a specified delay distribution, a specified beam distribution, etc.). The second characteristic information requirements of the second device are related to the second characteristic information, including a specified second characteristic distribution.

[0168] Optionally, the first device may send multiple distributed training request messages to multiple second devices by unicast (such as a central node sending point-to-point messages to each child node); or may send them by broadcast / multicast, thereby reducing transmission overhead (compared to unicast, transmission overhead can be reduced).

[0169] S402, multiple second devices determine whether the training requirements are met based on their respective distributed training request messages and their respective data.

[0170] For example, child node X can determine whether its own computing power information meets the requirements based on the computing power requirement / latency requirement in the distributed training request message. If so, it is determined that child node X meets the training requirements. For another example, child node X can determine whether its own first feature information / second feature information meets the requirements based on the first feature information requirement / second feature information requirement in the distributed training request message. If not, it is determined that child node X does not meet the training requirements.

[0171] S403: The multiple second devices send first indication information of the multiple second devices to the first device.

[0172] The first indication information includes confirmation indication information or rejection indication information.

[0173] The confirmation indication information is used to indicate one or more of the following information: the quality information of the data corresponding to the second device meets the quality requirements, the environmental information of the second device meets the environmental requirements, the computing power of the second device meets the minimum computing power requirements, the communication capability information of the second device meets the minimum communication capability requirements, the first characteristic information of the data corresponding to the second device meets the first characteristic information requirements, and the second characteristic information of the data corresponding to the second device meets the second characteristic information requirements.

[0174] The rejection indication information is used to indicate one or more of the following information: the quality information of the data corresponding to the second device does not meet the quality requirements, the environmental information of the second device does not meet the environmental requirements, the computing power of the second device does not meet the minimum computing power requirements, the communication capability information of the second device does not meet the minimum communication capability requirements, the first characteristic information of the data corresponding to the second device does not meet the first characteristic information requirements, and the second characteristic information of the data corresponding to the second device does not meet the second characteristic information requirements.

[0175] For example, if the latency requirement is that the communication latency of a child node be less than 100ms, child node X can determine whether it meets this latency requirement. If it does (for example, the communication latency of child node X is less than 100ms), child node X can send an ACK message back to the central node. If it does not (for example, the communication latency of child node X is greater than 100ms), child node X can send a NACK message back to the central node.

[0176] It can be understood that in this embodiment, the child nodes make decisions (for example, the child nodes decide whether to perform distributed training), which requires lower computing power from the central node and is conducive to reducing uplink and downlink overhead.

[0177] S404: The first device determines the second devices that participate in the distributed training according to the first indication information of the plurality of second devices.

[0178] For example, based on multiple first indication messages fed back by child nodes 1 to X, the central node schedules all or part of the child nodes whose first indication message is confirmation indication message to participate in distributed training; or, schedules all or part of the child nodes whose first indication message is not rejection indication message or who have not fed back rejection indication message to participate in distributed training.

[0179] Optionally, after S404, the following steps are further included:

[0180] S405: The first device sends a scheduling request message to the second device participating in the distributed training.

[0181] The specific implementation of S405 can refer to the corresponding description in S404 and will not be repeated here.

[0182] It is understandable that the above examples 1 to 3 can be executed separately or in combination. For example, assuming that the child node feeds back training status information and data status information to the central node (combined with the processes of example 1 and example 2), the central node can schedule the corresponding child node to participate in distributed training based on the training status information and the first weight of the training status information, as well as the data status information and the second weight of the data status information. The specific scheduling method can refer to the corresponding description in the previous embodiment, which will not be repeated here.

[0183] In order to realize the various functions in the method provided by the present application, the device or equipment provided by the present application may include a hardware structure and / or a software module, and realize the above-mentioned various functions in the form of a hardware structure, a software module, or a hardware structure plus a software module. Whether a certain function among the above-mentioned 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. The division of modules in the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, the various functional modules in the various embodiments of the present application can be integrated into a processor, or they can exist physically separately, or two or more modules can be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software functional modules.

[0184] Figure 6 is a schematic diagram of a communication device provided by the present application. The device may include a module corresponding to each of the methods / operations / steps / actions described in any of the embodiments shown in Figures 2 to 5. The module may be implemented as a hardware circuit, software, or a combination of hardware circuits and software.

[0185] The apparatus 600 includes a communication unit 601 and a processing unit 602, and is configured to implement the methods executed by the various devices in the aforementioned embodiments.

[0186] In one possible implementation, the device is a first device, which may be a central node of a training network (such as a base station, a terminal, etc.), or located in a central node of a training network (such as a base station, a terminal, etc.). Specifically, the communication unit 601 is used to send multiple first messages, and the multiple first messages are used to request multiple second devices to perform distributed training. The communication unit 601 is also used to receive multiple second messages, and any second message among the multiple second messages includes one or more of the following information: training status information of the second device corresponding to the second message, data status information of the second device corresponding to the second message, and first indication information indicating whether the second device corresponding to the second message meets the training requirements. The processing unit 602 is used to schedule the second device participating in the distributed training based on the multiple second messages.

[0187] The specific execution process of the communication unit 601 and the processing unit 602 in this embodiment can refer to the description of the steps executed by the central node of the training network in the method embodiment above, as well as the corresponding description in the invention content, which will not be repeated here. In the communication method implemented by this device, through the information feedback of the second device (such as the sub-node in the training network), the first device (such as the central node in the training network) can better plan and schedule the sub-nodes for distributed training, which is conducive to improving the efficiency of distributed training.

[0188] In one possible implementation, the device is a second device, which may be a sub-node of the training network (such as a base station, a terminal, etc.), or located in a sub-node of the training network (such as a base station, a terminal, etc.). Specifically, the communication unit 601 is used to receive a first message, which is used to request the second device to perform distributed training. The communication unit 601 is also used to send a second message, which includes one or more of the following information: training status information of the second device, data status information of the second device, and first indication information indicating whether the second device meets the training requirements. The processing unit 602 is used to participate in distributed training according to the scheduling of the first device.

[0189] The specific execution process of the communication unit 601 and the processing unit 602 in this embodiment can refer to the description of the steps executed by the sub-nodes of the training network in the method embodiment above, as well as the corresponding description in the invention summary, and will not be repeated here. In the communication method implemented by this device, the second device can feedback training and / or data-related information to the first device, which helps the first device better plan and schedule sub-nodes for distributed training, thereby improving the efficiency of distributed training.

[0190] Figure 7 is a schematic diagram of another communication device provided by the present application, which is used to implement the communication methods in the above-mentioned method embodiments. It can be understood that the communication device 700 includes necessary forms such as modules, units, elements, circuits, or interfaces, which are appropriately configured together to perform the methods in the present application. For example, the communication device 700 can be a functional entity such as an enabling server, an enabling client, a transmission server, an application server, etc., or it can be a component (such as a chip) in a functional entity to implement the method described in the above method embodiments. The communication device 700 includes one or more processors 701. The processor 701 can be a general-purpose processor or a dedicated processor. For example, it can be a baseband processor or a central processing unit. The baseband processor can be used to process the communication protocol and communication data, and the central processing unit can be used to control the communication device, execute the software program, and process the data of the software program.

[0191] Optionally, the processor 701 may include a program 702 (sometimes also referred to as code or instructions), which may be executed on the processor 701 to enable the communication device 700 to perform the method described in the above embodiments. In another possible design, the communication device 700 includes a circuit (not shown in FIG. 7 ) that is used to implement the functions of the enabling server, enabling client, transmission server, application server, and other functional entities in the above embodiments.

[0192] Optionally, the communication device 700 may include one or more memories 703 storing programs 704 (sometimes also referred to as codes or instructions). The programs 704 may be executed on the processor 701 to enable the communication device 700 to perform the methods described in the above method embodiments.

[0193] Optionally, processor 701 and / or memory 703 may include AI modules 705 and 706, which are used to implement AI-related functions. The AI ​​module may be implemented using software, hardware, or a combination of software and hardware. For example, the AI ​​module may include a real-time information processing (RIC) module. For example, the AI ​​module may be a near-real-time RIC or a non-real-time RIC.

[0194] Optionally, the communication device 700 further includes a transceiver 707 and an antenna 708. The transceiver 707 and the antenna 708 can implement transceiver functions, such as communicating with other devices via a transmission medium, so that the communication device 700 can communicate with other devices.

[0195] In one possible implementation, the device is a first device, which may be a central node of a training network (such as a base station, a terminal, etc.), or located in a central node of a training network (such as a base station, a terminal, etc.). Specifically, the transceiver 707 and the antenna 708 are used to send multiple first messages, and the multiple first messages are used to request multiple second devices to perform distributed training. The transceiver 707 and the antenna 708 are also used to receive multiple second messages, and any second message among the multiple second messages includes one or more of the following information: training status information of the second device corresponding to the second message, data status information of the second device corresponding to the second message, and first indication information indicating whether the second device corresponding to the second message meets the training requirements. The processor 701 is used to schedule the second device participating in the distributed training according to the multiple second messages.

[0196] The specific execution process of the communication device 700 in this embodiment can refer to the description of the steps executed by the central node of the training network in the method embodiment above, as well as the corresponding description in the invention content, and will not be repeated here. In the communication method implemented by this device, through information feedback from the second device (such as the sub-node in the training network), the first device (such as the central node in the training network) can better plan and schedule the sub-nodes for distributed training, which is conducive to improving the efficiency of distributed training.

[0197] In one possible implementation, the device is a second device, which may be a sub-node of the training network (such as a base station, a terminal, etc.), or located in a sub-node of the training network (such as a base station, a terminal, etc.). Specifically, the transceiver 707 and the antenna 708 are used to receive a first message, which is used to request the second device to perform distributed training. The transceiver 707 and the antenna 708 are also used to send a second message, which includes one or more of the following information: training status information of the second device, data status information of the second device, and first indication information indicating whether the second device meets the training requirements. The processor 701 is used to participate in distributed training according to the scheduling of the first device.

[0198] The specific execution process of the communication device 700 in this embodiment can refer to the description of the steps executed by the sub-nodes of the training network in the method embodiment above, as well as the corresponding description in the Summary of the Invention, and will not be repeated here. In the communication method implemented by this device, the second device can feedback training and / or data-related information to the first device, which helps the first device better plan and schedule sub-nodes for distributed training, thereby improving the efficiency of distributed training.

[0199] In this application, a processor may be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, and may implement or execute the methods, steps, and logic block diagrams disclosed in this application. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in this application may be directly executed by a hardware processor, or by a combination of hardware and software modules within the processor.

[0200] In the present application, the memory may be a non-volatile memory, such as a hard disk drive (HDD) or a solid-state drive (SSD), or a volatile memory, such as a random-access memory (RAM). The memory is any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory in the present application may also be a circuit or any other device that can implement a storage function, for storing program instructions and / or data.

[0201] The present application provides another communication device, which includes a processor and an interface. Optionally, it also includes a memory, the processor is coupled to the memory, and the processor is used to read and execute computer instructions stored in the memory to implement the communication method in the embodiments shown in Figures 2 to 5.

[0202] The present application provides a communication system, which includes one or more entities or devices in the embodiments shown in Figures 2 to 5.

[0203] The present application provides a computer-readable storage medium. The computer-readable storage medium stores a program or instruction. When the program or instruction is executed on a computer, the computer executes the communication method in the embodiments shown in Figures 2 to 5.

[0204] The present application provides a computer program product. The computer program product includes instructions. When the instructions are executed on a computer, the computer executes the communication method in the embodiments shown in Figures 2 to 5.

[0205] The present application provides a chip or chip system, which includes at least one processor and an interface, the interface and the at least one processor are interconnected by lines, and the at least one processor is used to run computer programs or instructions to execute the communication method in the embodiments shown in Figures 2 to 5.

[0206] The interface in the chip may be an input / output interface, a pin, or a circuit.

[0207] The chip system may be a system on chip (SOC) or a baseband chip, wherein the baseband chip may include a processor, a channel encoder, a digital signal processor, a modem, an interface module, and the like.

[0208] In one implementation, the chip or chip system described above in this application further includes at least one memory, in which instructions are stored. The memory may be a storage unit within the chip, such as a register, a cache, etc., or a storage unit of the chip (e.g., a read-only memory, a random access memory, etc.).

[0209] The technical solutions provided in this application can be implemented in whole or in part through software, hardware, firmware, or any combination thereof. When implemented using software, they can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in this application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a terminal device, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital video disc (DVD)), or a semiconductor medium.

[0210] In this application, under the premise that there is no logical contradiction, the various embodiments may reference each other, for example, the methods and / or terms between method embodiments may reference each other, for example, the functions and / or terms between device embodiments may reference each other, for example, the functions and / or terms between device embodiments and method embodiments may reference each other.

[0211] 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.

Claims

1. A communication method, characterized in that: include: Sending a plurality of first messages, where the plurality of first messages are used to request a plurality of second devices to perform distributed training; receiving a plurality of second messages, wherein any second message of the plurality of second messages includes one or more of the following information: training state information of a second device corresponding to the second message, data state information of the second device corresponding to the second message, and first indication information indicating whether the second device corresponding to the second message meets a training requirement; According to the plurality of second messages, a second device participating in the distributed training is scheduled.

2. The method according to claim 1, characterized in that The first message includes second indication information, and the second indication information is used to indicate that a second device corresponding to the request is to perform distributed training.

3. The method according to claim 2, characterized in that The first message further includes one or more of the following information: full model parameters trained at the current moment, corresponding sub-model parameters of the second device trained at the current moment, and training round information; The training round information includes a first training number for requesting the second device to perform a complete training or a parameter update on all training samples, and / or a second training number for requesting the second device to perform a complete training or a parameter update on part of the training samples.

4. The method according to any one of claims 1 to 3, characterized in that: The training state information of the second device corresponding to the second message includes convergence information obtained by the second device through training updates of the first training times and / or the second training times according to the training model at the current moment and the corresponding data; The convergence information includes cross-validation accuracy or cross-validation test error.

5. The method according to claim 1 or 2, characterized in that: The data status information includes one or more of the following information: quality information of data corresponding to the second device, environment information of the second device, first characteristic information of data corresponding to the second device, second characteristic information of data corresponding to the second device, computing power information of the second device, and communication capability information of the second device; The quality information of the data corresponding to the second device includes one or more of the following information: a signal-to-noise ratio of the data corresponding to the second device, a signal-to-interference-to-noise ratio of the data corresponding to the second device, and a number of samples of the data corresponding to the second device; The environmental information of the second device includes location information and / or environmental parameters of the second device; The first characteristic information of the data corresponding to the second device includes a first characteristic distribution of the data corresponding to the second device; The second feature information of the data corresponding to the second device includes a second feature distribution obtained by extracting features from the data corresponding to the second device; The computing power information of the second device includes one or more of the following information: the computing latency of the second device, the number of operations that can be performed per unit time, and the number of multiplications / additions that can be performed per unit time; The communication capability information of the second device includes one or more of the following information: communication delay of the second device, channel quality indication corresponding to the second device, rank indication of the channel corresponding to the second device, and reference signal receiving power of the channel corresponding to the second device.

6. The method according to claim 1 or 2, characterized in that: The first message also includes one or more of the following information: Quality requirements for data corresponding to the second device, environmental requirements for the second device, minimum computing power requirements for the second device, minimum communication capability requirements for the second device, first characteristic information requirements for data corresponding to the second device, and second characteristic information requirements for data corresponding to the second device.

7. The method according to claim 6, characterized in that The first indication information includes confirmation indication information or rejection indication information; The confirmation indication information is used to indicate one or more of the following information: the quality information of the data corresponding to the second device meets the quality requirement, the environment information of the second device meets the environment requirement, the computing power of the second device meets the minimum computing power requirement, the communication capability information of the second device meets the minimum communication capability requirement, the first feature information of the data corresponding to the second device meets the first feature information requirement, and the second feature information of the data corresponding to the second device meets the second feature information requirement; The rejection indication information is used to indicate one or more of the following information: the quality information of the data corresponding to the second device does not meet the quality requirement, the environmental information of the second device does not meet the environmental requirement, the computing power of the second device does not meet the minimum computing power requirement, the communication capability information of the second device does not meet the minimum communication capability requirement, the first feature information of the data corresponding to the second device does not meet the first feature information requirement, and the second feature information of the data corresponding to the second device does not meet the second feature information requirement.

8. The method according to any one of claims 1 to 7, characterized in that: The types of the training state information, the data state information, and the first indication information are different; Scheduling a second device participating in the distributed training according to the plurality of second messages includes: When the plurality of second messages include at least two types of information, the second devices participating in the distributed training are scheduled according to the various types of information included in the plurality of second messages and weights of the various types of information.

9. A communication method, characterized in that: include: receiving a first message, wherein the first message is used to request a second device to perform distributed training; sending a second message, wherein the second message includes one or more of the following information: training status information of the second device, data status information of the second device, and first indication information indicating whether the second device meets the training requirement; Participate in distributed training according to the scheduling of the first device.

10. The method according to claim 9, characterized in that The first message further includes one or more of the following information: full model parameters trained at the current moment, sub-model parameters of the second device trained at the current moment, and training round information; The training round information includes a first training number for requesting the second device to perform a complete training or a parameter update on all training samples, and / or a second training number for requesting the second device to perform a complete training or a parameter update on part of the training samples.

11. The method according to claim 9 or 10, characterized in that: The training state information includes convergence information obtained by the second device through training updates of the first training times and / or the second training times according to the training model at the current moment and the corresponding data; The convergence information includes cross-validation accuracy or cross-validation test error.

12. The method according to claim 9, characterized in that The data status information includes one or more of the following information: data quality information corresponding to the second device, environment information of the second device, first feature information of data corresponding to the second device, second feature information of data corresponding to the second device, computing power information of the second device, and communication capability information of the second device; The data quality information corresponding to the second device includes one or more of the following information: a signal-to-noise ratio of the data corresponding to the second device, a signal-to-interference-to-noise ratio of the data corresponding to the second device, and a sample quantity of the data corresponding to the second device; The environmental information of the second device includes location information and / or environmental parameters of the second device; The first characteristic information of the data corresponding to the second device includes a first characteristic distribution of the data corresponding to the second device; The second feature information of the data corresponding to the second device includes a second feature distribution obtained by extracting features from the data corresponding to the second device; The computing power information of the second device includes one or more of the following information: the computing latency of the second device, the number of operations that can be performed per unit time, and the number of multiplications / additions that can be performed per unit time; The communication capability information of the second device includes one or more of the following information: communication delay of the second device, channel quality indication corresponding to the second device, rank indication of the channel corresponding to the second device, and reference signal receiving power of the channel corresponding to the second device.

13. The method according to claim 9, characterized in that The first message also includes one or more of the following information: Quality requirements for data corresponding to the second device, environmental requirements for the second device, minimum computing power requirements for the second device, minimum communication capability requirements for the second device, first characteristic information requirements for data corresponding to the second device, and second characteristic information requirements for data corresponding to the second device.

14. The method according to claim 13, characterized in that The first indication information includes confirmation indication information or rejection indication information; The confirmation indication information is used to indicate one or more of the following information: quality information of the data corresponding to the second device meets the quality requirement, environment information of the second device meets the environment requirement, computing power of the second device meets the minimum computing power requirement, communication capability information of the second device meets the minimum communication capability requirement, first feature information of the data corresponding to the second device meets the first feature information requirement, and second feature information of the data corresponding to the second device meets the second feature information requirement; The rejection indication information is used to indicate one or more of the following information: the quality information of the data corresponding to the second device does not meet the quality requirement, the environmental information of the second device does not meet the environmental requirement, the computing power of the second device does not meet the minimum computing power requirement, the communication capability information of the second device does not meet the minimum communication capability requirement, the first feature information of the data corresponding to the second device does not meet the first feature information requirement, and the second feature information of the data corresponding to the second device does not meet the second feature information requirement.

15. A communication device, characterized in that: The method comprises a communication unit and a processing unit, wherein the communication unit and the processing unit are used to execute the method according to any one of claims 1 to 8 or 9 to 14.

16. A communication device, characterized in that: include: A processor and a memory, wherein the memory is used to store instructions, and when the instructions are executed by the processor, the communication device executes the method according to any one of claims 1 to 8 or 9 to 14.

17. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed on a computer, the computer is caused to perform the method according to any one of claims 1 to 8 or 9 to 14.

18. A chip system, characterized in that: The chip system comprises a processor and an interface, wherein the processor is configured to execute a computer program so that the chip system implements the method as claimed in any one of claims 1 to 8 or 9 to 14.

19. A computer program product, characterized in that The method comprises instructions which, when executed on a computer, cause the computer to perform the method according to any one of claims 1 to 8 or 9 to 14.

Images