Electronic device and method for wireless communication, and computer-readable storage medium

Abstract

The present application relates to an electronic device and a method for wireless communication, and a computer-readable storage medium. The electronic device for wireless communication comprises a processing circuit, wherein the processing circuit is configured to determine, according to state information reported by a user equipment within a service range of the electronic device, whether the user equipment is to cooperate with other user equipments to train a segmented model obtained by segmenting a model to be trained, so as to participate in federated learning in a non-independent way, or to independently train the model to be trained, so as to independently participate in federated learning. (FIG. 1)

Description

Electronic device and method for wireless communication, and computer-readable storage medium

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on March 31, 2023, with application number 202310342408.6 and invention name “Electronic device and method for wireless communication, computer-readable storage medium”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present disclosure relates to the field of wireless communication technology, and more particularly to an electronic device and method for wireless communication, and a computer-readable storage medium. More particularly, the present disclosure relates to more efficient federated learning. Background Art

[0003] During federated learning (FL), a user device uploads a local learning model to a base station or server for model aggregation. In some cases (e.g., insufficient computing or communication capabilities of the user device), federated learning may not be effective.

[0004] How to conduct federated learning more effectively is a current research hotspot.

[0005] Summary of the Invention

[0006] A brief overview of the present invention is provided below to provide a basic understanding of certain aspects of the present invention. It should be understood that this overview is not an exhaustive overview of the present invention. It is not intended to identify key or important aspects of the present invention, nor is it intended to limit the scope of the present invention. Its purpose is simply to present certain concepts in a simplified form as a prelude to the more detailed description discussed later.

[0007] According to one aspect of the present disclosure, an electronic device for wireless communication is provided, which includes a processing circuit, and the processing circuit is configured to: determine, based on the user device's own status information reported by the user device within the service range of the electronic device, whether the user device should cooperate with other user devices to train a segmented model obtained by segmenting the model to be trained, thereby participating in federated learning non-independently, or independently train the model to be trained, thereby participating in federated learning independently.

[0008] In an embodiment according to the present disclosure, the electronic device enables more efficient federated learning by determining whether the user device is to participate in federated learning non-independently or independently.

[0009] According to one aspect of the present disclosure, an electronic device for wireless communication is provided, which includes a processing circuit, and the processing circuit is configured to: report the electronic device's own status information to a network-side device that provides services for the electronic device, so that the network-side device can determine, in federated learning, whether the electronic device should cooperate with other electronic devices to train a segmented model obtained by segmenting a model to be trained, thereby participating in federated learning non-independently, or whether the electronic device should independently train the model to be trained, thereby participating in federated learning independently.

[0010] In an embodiment of the present disclosure, an electronic device reports its own status information to a network-side device so that the network-side device can determine whether the electronic device should participate in federated learning non-independently or independently, thereby enabling federated learning to be performed more efficiently.

[0011] According to one aspect of the present disclosure, an electronic device for wireless communication is provided, which includes a processing circuit, and the processing circuit is configured to: report the electronic device's own status information to a network-side device that provides services for the electronic device, so that the network-side device can determine, in federated learning, whether the electronic device can cooperate with other electronic devices to train a segmented model obtained by segmenting a model to be trained, so that other electronic devices participate in federated learning non-independently, or whether other electronic devices need to independently train the model to be trained, thereby independently participating in federated learning.

[0012] In an embodiment according to the present disclosure, an electronic device reports its own status information to a network-side device so that the network-side device can determine whether other electronic devices should participate in federated learning non-independently or independently, thereby enabling federated learning to be performed more efficiently.

[0013] According to one aspect of the present disclosure, a wireless communication system is provided. The wireless communication system includes the above electronic device.

[0014] According to one aspect of the present disclosure, a method for wireless communication is provided, comprising: determining, based on state information reported by a user device within a service range of the electronic device, whether, in federated learning, the user device is to cooperate with other user devices to train a segmented model obtained by segmenting a model to be trained, thereby participating in federated learning non-independently, or to independently train the model to be trained, thereby participating in federated learning independently.

[0015] According to one aspect of the present disclosure, a method for wireless communication is provided, comprising: reporting status information of an electronic device to a network-side device that provides services for the electronic device, so that the network-side device can determine whether, in federated learning, the electronic device should cooperate with other electronic devices to train a segmented model obtained by segmenting a model to be trained, thereby participating in federated learning non-independently, or whether the electronic device should independently train the model to be trained, thereby participating in federated learning independently.

[0016] According to one aspect of the present disclosure, a method for wireless communication is provided, comprising: reporting status information of an electronic device to a network-side device that provides services for the electronic device, so that the network-side device can determine, in federated learning, whether the electronic device can cooperate with other electronic devices to train a segmented model obtained by segmenting a model to be trained, so that the other electronic devices participate in the federated learning non-independently, or whether the other electronic devices need to independently train the model to be trained, thereby independently participating in the federated learning.

[0017] According to other aspects of the present invention, a computer program code and a computer program product for implementing the above-mentioned method for wireless communication, as well as a computer-readable storage medium having the computer program code for implementing the above-mentioned method for wireless communication recorded thereon are also provided. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to further illustrate the above and other advantages and features of the present invention, the following is a further detailed description of specific embodiments of the present invention in conjunction with the accompanying drawings. The accompanying drawings, together with the detailed description below, are included in this specification and form a part of this specification. Elements with the same function and structure are represented by the same reference numerals. It should be understood that these drawings only depict typical examples of the present invention and should not be regarded as limiting the scope of the present invention. In the drawings:

[0019] FIG1 shows a functional module block diagram of an electronic device for wireless communication according to an embodiment of the present disclosure;

[0020] FIG2 is a diagram illustrating an example of a federated learning network;

[0021] FIG3 is a diagram illustrating an example of segmentation learning according to an embodiment of the present disclosure;

[0022] FIG4 is a diagram illustrating examples of different segmentation points according to an embodiment of the present disclosure;

[0023] FIG5 is a diagram illustrating a structural example of a federated learning network according to an embodiment of the present disclosure;

[0024] FIG6 shows a functional module block diagram of an electronic device for wireless communication according to another embodiment of the present disclosure;

[0025] FIG7 shows a functional module block diagram of an electronic device for wireless communication according to yet another embodiment of the present disclosure;

[0026] FIG8 shows a flowchart of a method for wireless communication according to one embodiment of the present disclosure;

[0027] FIG9 shows a flowchart of a method for wireless communication according to another embodiment of the present disclosure;

[0028] FIG10 shows a flowchart of a method for wireless communication according to yet another embodiment of the present disclosure;

[0029] FIG11 is a block diagram showing a first example of a schematic configuration of an eNB or gNB to which the technology of the present disclosure may be applied;

[0030] FIG12 is a block diagram illustrating a second example of a schematic configuration of an eNB or gNB to which the technology of the present disclosure may be applied;

[0031] FIG13 is a block diagram showing an example of a schematic configuration of a smartphone to which the technology of the present disclosure can be applied;

[0032] FIG14 is a block diagram showing an example of a schematic configuration of a car navigation device to which the technology of the present disclosure can be applied; and

[0033] 15 is a block diagram of an exemplary structure of a general-purpose personal computer in which the method and / or apparatus and / or system according to the embodiments of the present invention may be implemented. DETAILED DESCRIPTION

[0034] Exemplary embodiments of the present invention are described below with reference to the accompanying drawings. For the sake of clarity and conciseness, not all features of an actual implementation are described in this specification. However, it should be understood that in the process of developing any such actual implementation, many implementation-specific decisions must be made in order to achieve the developer's specific goals, such as meeting system and business-related constraints, which may vary from implementation to implementation. Furthermore, it should be understood that while development work may be complex and time-consuming, it will be a routine task for those skilled in the art who benefit from this disclosure.

[0035] It is also necessary to explain here that, in order to avoid obscuring the present invention due to unnecessary details, the accompanying drawings only show the device structure and / or processing steps that are closely related to the solution according to the present invention, while other details that are not closely related to the present invention are omitted.

[0036] FIG1 shows a functional module block diagram of an electronic device 100 for wireless communication according to an embodiment of the present disclosure.

[0037] As shown in Figure 1, the electronic device 100 includes: a processing unit 101, which can determine, based on the user device's own status information reported by the user device within the service range of the electronic device 100, whether the user device should cooperate with other user devices to train the segmented model obtained by segmenting (splitting) the model to be trained, thereby participating in federated learning non-independently, or independently train the model to be trained, thereby independently participating in federated learning.

[0038] The processing unit 101 may be implemented by one or more processing circuits, which may be implemented as a chip, for example.

[0039] The electronic device 100 can serve as a network side device in a wireless communication system, and specifically, for example, can be set on the base station side or communicatively connected to the base station. Here, it should also be pointed out that the electronic device 100 can be implemented at the chip level, or it can also be implemented at the device level. For example, the electronic device 100 can work as the base station itself, and can also include external devices such as memory, transceiver (not shown), etc. The memory can be used to store programs and related data information that need to be executed by the base station to implement various functions. The transceiver may include one or more communication interfaces to support communication with different devices (for example, user equipment (UE), other base stations, etc.), and the implementation form of the transceiver is not specifically limited here.

[0040] As an example, the network side device may also be a base station, which may be, for example, an eNB or a gNB.

[0041] As an example, the network-side device may also be a server.

[0042] The wireless communication system according to the present disclosure may be a 5G NR (New Radio) communication system. Furthermore, the wireless communication system according to the present disclosure may include a non-terrestrial network (NTN). Optionally, the wireless communication system according to the present disclosure may also include a terrestrial network (TN). In addition, those skilled in the art will appreciate that the wireless communication system according to the present disclosure may also be a 4G or 3G communication system.

[0043] As an example, the model to be trained can be a deep learning model, such as at least one of an RNN (recurrent neural network), a CNN (convolutional neural network), and an ANN (artificial neural network). Hereinafter, for simplicity, the model to be trained is sometimes referred to as a model.

[0044] For example, the user equipment estimates its own state information Info UAnd report it to the electronic device 100.

[0045] FIG2 is a diagram illustrating an example of a federated learning network.

[0046] As shown in Figure 2, assume that there are K (where K is a positive integer greater than 1) user devices (device 1, device 2, device 3, ..., device K-1, device K). The federated learning process of the federated learning network is as follows: (1) Each user device accesses the server (Server) or base station (hereinafter, for simplicity, the base station is used as an example) through a wireless channel, and obtains the parameters of the initial global model (w 0 ) as the parameters of the initial local model: in, represents the parameters of the initial local model of device k (k = 1, 2, ..., K). In the following, for simplicity, the parameters of the global model are sometimes referred to as the global model, and the parameters of the local model are sometimes referred to as the local model. (2) Each user device uses the locally stored data to learn and complete an iterative update of the local model (local update): in, represents the local model of device k at time t, represents the gradient of the local model of device k, represents the local model of device k at time t+1, η represents the predetermined parameters, and represents the loss function of the local model of device k; (3) Each user device transmits the learned local model through the uplink or gradient Upload them to the base station respectively; (4) The base station aggregates the local models collected from each user device Complete a global model aggregation, where p k represents the weight coefficient corresponding to the local model of device k, usually set to D k represents the number of local samples of device k; (5) The base station updates the global model (aggregated global model) w t+1 It is sent to each user device again (global update), and steps (2) to (5) are repeated until the global model converges.

[0047] For example, the above-mentioned model to be trained corresponds to the initial global model or the updated global model involved in FIG2 .

[0048] A user device that independently participates in federated learning can be referred to as a standalone member in federated learning. In addition, a non-standalone member in federated learning is also defined. The non-standalone member includes a UE that participates in federated learning non-independently and the other user devices mentioned above that cooperate with the UE. Other user devices that form a non-standalone member with the UE can be referred to as assistant equipment (AE). For example, an assistant device can be a peripheral device of the UE. In the following, the standalone member and the non-standalone member are sometimes collectively referred to as members.

[0049] 3 is a diagram illustrating an example of segmentation learning according to an embodiment of the present disclosure, wherein in segmentation learning (split learning), a model to be trained is segmented to obtain segmented models, and the segmented models are trained.

[0050] First, establish the model topology. As shown in Figure 3, the complete model to be trained is divided into two parts at the split point, namely the front layer model (first split model) on the left and the back layer model (second split model) on the right. Assuming that the UE trains the first split model and the AE trains the second split model, for simplicity, the first split model can be referred to as the UE model, and the second split model can be referred to as the AE model. That is, the complete model to be trained is divided between the UE and the AE, and split into the UE model and the AE model. It should be noted that although the model is shown to be divided into two parts in Figure 3, those skilled in the art will understand that the model can be divided into other integer numbers of parts.

[0051] At the beginning of training, the training parameters for both the UE model and the AE model are randomly initialized.

[0052] During training, the UE performs forward computation on the UE model based on local data and sends the local label and intermediate data #1 (e.g., the output tensor of the UE model) obtained from the forward computation to the AE. After obtaining intermediate data #1, the AE continues forward computation on the AE model and performs reverse gradient calculation based on the uploaded label to obtain the gradient corresponding to the AE model. The AE then updates the AE model parameters based on the obtained gradient. The AE then transmits intermediate data #2 (e.g., the gradient of the AE model) back to the UE, where the UE continues reverse computation to obtain the gradient corresponding to the UE model. The UE then updates the UE model parameters based on the gradient corresponding to the UE model. This cycle repeats until the model converges. In summary, 1) the UE first runs the UE model (performs the forward propagation algorithm) and transmits the resulting intermediate data #1 to the AE. 2) the AE uses the received intermediate data #1 as input to the AE model and first runs the forward propagation algorithm to obtain the intermediate result. Then, based on the intermediate result, the AE runs the reverse propagation algorithm to obtain intermediate data #2 (e.g., the gradient of the AE model) and updates the AE model. The AE transmits intermediate data #2 back to the UE. 3) The UE runs the backpropagation algorithm based on intermediate data #2 to update the UE model. Steps 1)–3) may be repeated several times in each round of global training in federated learning.

[0053] In the broadcast case, the UE can first perform one or several complete local model updates, and then send the updated AE model to the AE for segmentation learning to improve the privacy protection of the UE's local data.

[0054] If the user device is a Standalone Member, it does not participate in segmented learning, but instead independently trains the complete model to be trained locally. Its trained local model is then aggregated with the trained local models of other Members to perform global model aggregation for federated learning. Alternatively, the user device can form a Non-Standalone Member with the aforementioned AE to perform segmented learning of the model to be trained locally, and the trained local model of the Non-Standalone Member is aggregated with the trained local models of other Members to perform global model aggregation for federated learning.

[0055] Both Standalone Member and Non-Standalone Member are equivalent to clients in traditional federated learning networks. Compared to clients in traditional federated learning networks, Non-Standalone Member adds both UEs and AEs. By splitting the model to be trained, some of the model that originally needed to be trained on the UE is placed on the AE to complete the training.

[0056] In an embodiment of the present disclosure, the electronic device 100 determines whether the user equipment is to participate in federated learning non-independently or independently, so that federated learning can be performed more efficiently. For example, the computing or communication of different UEs participating in federated learning is heterogeneous. Some UEs carry important data but have insufficient computing or communication capabilities, while some UEs have strong computing and communication capabilities. For example, for UEs with insufficient computing or communication capabilities, the burden on the UE in the process of participating in federated learning can be reduced by cooperating with other user equipment (AE) to train the segmented model; UEs with strong computing and communication capabilities can complete the training of the model to be trained locally independently without cooperating with AE. In addition, the computing or communication resources of AE in the communication network can also be fully utilized. In addition, the number of users participating in federated learning that the electronic device 100 can support is usually limited, so UE selection is required before the start of federated learning. Some devices that are not selected but still want to participate in federated learning (contribute to federated learning) can participate in training as AE. For Non-Standalone Member, the AE only has part of the model parameters of the model to be trained. The intermediate data is transmitted between the UE and the AE, which ensures the privacy and security of the data. That is, data privacy protection is further improved.

[0057] For example, AE can be a device with considerable computing power in a communication network. For example, when a mobile phone serves as a UE, a vehicle and an unmanned aerial vehicle (UAV) can serve as an AE. When a vehicle serves as a UE, a roadside unit (RSU) can serve as an AE, and so on.

[0058] As an example, the user device's own state information includes first channel state information of the link between the user device and the electronic device 100, and the processing unit 101 can be configured to determine that the user device is to participate in federated learning non-independently when the value of the first channel state information is less than a first predetermined threshold.

[0059] For example, those skilled in the art may set the first predetermined threshold based on experience or application scenarios.

[0060] As an example, the first channel state information includes at least one of a signal-to-interference and noise ratio (SINR), a reference signal received power (RSRP), a reference signal received quality (RSRQ), and a reference signal received intensity (RSRI) of the uplink between the user equipment and the electronic device 100.

[0061] Taking SINR as an example, when the uplink SINR is less than a first predetermined threshold, it is determined that the user equipment and other user equipments form a Non-Standalone Member to participate in federated learning.

[0062] As an example, the user device's state information includes computing and storage capability information of the user device, and the processing unit 101 may be configured to determine that the user device should participate in federated learning non-standalone if the storage space size indicated by the computing and storage capability information is smaller than the size of the model to be trained, and / or the computing capability indicated by the computing and storage capability information is smaller than the computing capability required to train the model to be trained. That is, in the above case, it is determined that the user device should form a non-standalone member with other user devices to participate in federated learning.

[0063] As an example, the computing and storage capability information includes at least one of a CPU occupancy rate and a memory size of the user equipment.

[0064] As an example, the user device's own state information includes local data information of the user device, and the processing unit 101 can be configured to determine that the user device is to participate in federated learning non-standalone when a training time required for the user device to train a model to be trained is greater than a second predetermined threshold, where the training time is obtained based on the local data information and computing and storage capacity information of the user device. That is, when the training time is greater than the second predetermined threshold, it is determined that the user device is to be formed into a non-standalone member with other user devices to participate in federated learning.

[0065] For example, those skilled in the art may set the second predetermined threshold based on experience or application scenarios.

[0066] As an example, the local data information includes the number of training samples and sample dimensions that the user device will use when independently participating in federated learning.

[0067] As an example, the user device's own state information includes power information of the user device, and the processing unit 101 can be configured to determine that the user device is to participate in federated learning non-standalone when the power level indicated by the power level information is less than a third predetermined threshold. In other words, when the power level indicated by the power level information is less than the third predetermined threshold, it is determined that the user device is to form a non-standalone member with other user devices to participate in federated learning.

[0068] For example, those skilled in the art may set the third predetermined threshold based on experience or application scenarios.

[0069] As an example, the user device's state information includes the user device's location information, and the processing unit 101 may be configured to determine that the user device is to independently participate in federated learning if it is determined based on the location information that no other user devices are within a predetermined range of the user device. Specifically, if it is determined that no other user devices are within the predetermined range of the user device, the user device is determined to participate in federated learning as a Standalone Member.

[0070] For example, those skilled in the art may set the predetermined range based on experience or application scenarios.

[0071] As an example, the user device's state information includes mobility information of the user device, and the processing unit 101 may be configured to, if it is determined based on the mobility information that the user device has high mobility, determine that the user device should independently participate in federated learning. That is, if it is determined that the user device has high mobility, determine that the user device should participate in federated learning as a standalone member.

[0072] As an example, the movement information includes at least one of a moving speed, a moving direction, and a dwell time of the user equipment.

[0073] As an example, the processing unit 101 may be configured to, when determining that the user equipment is to participate in federated learning non-independently, select a user equipment to be coordinated with the user equipment for training based on second channel state information of a sidelink between the user equipment and other user equipment within a predetermined range of the user equipment. In other words, for the user equipment, the user equipment to be coordinated is not fixed. For example, the user equipment to be coordinated is the AE mentioned above.

[0074] As an example, the processing unit 101 may be configured to select the following other user equipment as the user equipment to be coordinated: the value of the second channel state information of the side link corresponding to the other user equipment is greater than a fourth predetermined threshold (AE selection condition 1).

[0075] For example, those skilled in the art may set the fourth predetermined threshold based on experience or application scenarios.

[0076] As an example, the second channel state information includes at least one of a signal to interference and noise ratio (SINR), a reference signal received power (RSRP), a reference signal received quality (RSRQ), and a reference signal received strength (RSRI) of the sidelink.

[0077] As an example, the processing unit 101 can be configured to select other user equipment (AE) that meets the following conditions as the user equipment to be cooperated based on the second channel state information: via the side link corresponding to the other user equipment, the user equipment (UE) can transmit model data related to the segmented model corresponding to the user equipment to the other user equipment within a first predetermined time range, and / or the other user equipment can transmit model data related to the segmented model corresponding to the other user equipment to the user equipment within a second predetermined time range (AE selection condition 2).

[0078] As an example, the model data associated with the segmented model corresponding to the UE may be the intermediate data #1 described in conjunction with FIG. 3 , and the model data associated with the segmented model corresponding to the AE may be the intermediate data #2 described in conjunction with FIG. 3 .

[0079] For example, those skilled in the art may set the first predetermined time range (for example, represented by t1) and / or the second predetermined time range (for example, represented by t2) according to experience or application scenarios.

[0080] As an example, the processing unit 101 may be configured to determine, based on the second channel state information, a split point (Split Point) for segmenting the model to be trained to obtain a segmented model when the user equipment (AE) to be coordinated is selected. The split point may include one or more split points. It should be noted that although it is described here that the split point is determined after the user equipment (AE) to be coordinated is selected, the user equipment (AE) to be coordinated may be selected when the split point has already been determined. In this case, the selection conditions may also include, for example, the AE selection condition 1 and / or the AE selection condition 2 described above.

[0081] For example, for Non-Standalone Member, the split point between UE and AE is determined in advance by the electronic device 100 based on the second channel state information.

[0082] FIG. 4 is a diagram illustrating examples of different segmentation points according to an embodiment of the present disclosure.

[0083] Assume that the model to be trained (e.g., a neural network) has M layers, and m represents the location of the split point. m = 0 indicates that the model to be trained is completely offloaded to the AE (the model to be trained is trained entirely at the AE), while m = M indicates that the model to be trained is not split and is therefore trained entirely at the UE. Figure 4 shows an example when M = 5.

[0084] For a Non-Standalone Member, 1). When m = 0, the model to be trained is completely offloaded to the AE. The AE side may have no data. The UE needs to transmit the original data to the AE, and only one transmission is required during the entire training process (for example, when there is no additional notification from the electronic device 100). After the AE completes local training, it can send the trained model back to the UE, and the UE uploads the trained local model to the electronic device 100 (for example, when the uplink state of the UE is good and the uplink state of the AE is poor). The AE can also directly upload the model to the electronic device 100. 2). When m = M, the model to be trained is completely trained at the UE, and at this time, the AE only acts as a relay (Relay). 3). When 0 < m < M, the UE and the AE exchange intermediate data through the sidelink for split learning.

[0085] As an example, the processing unit 101 may be configured such that the determined split point satisfies the following conditions: via the sidelink between the user equipment (UE) and the cooperating user equipment (AE), the user equipment can transmit the model data related to the split model corresponding to the user equipment to the cooperating user equipment within a first predetermined time range, and / or the cooperating user equipment can transmit the model data related to the split model corresponding to the cooperating user equipment to the user equipment within a second predetermined time range. For example, the model data related to the split model corresponding to the UE may be the intermediate data #1 described in conjunction with FIG. 3, and the model data related to the split model corresponding to the AE may be the intermediate data #2 described in conjunction with FIG. 3.

[0086] As an example, the own state information of the user equipment includes the second channel state information of the sidelink between other user equipment within a predetermined range of the user equipment and the user equipment. Since the sidelink between the UE and the AE changes over time, it is necessary to make dynamic decisions for federated learning according to the changes in the sidelink. For example, whether the UE participates in federated learning as a Standalone Member or a Non-standalone Member, which AE the UE forms a Non-standalone Member with, the position of the split point, etc., need to be dynamically determined according to the changes in the sidelink.

[0087] As an example, the processing unit 101 may be configured to determine that the user equipment participates in federated learning non-independently when there is other user equipment within a predetermined range whose value of the second channel state information is greater than a fifth predetermined threshold.

[0088] For example, those skilled in the art can set the fifth predetermined threshold according to experience or application scenarios.

[0089] As an example, the processing unit 101 may be configured to determine that the user equipment is to independently participate in federated learning when the second channel state information corresponding to other user equipments within a predetermined range is less than or equal to a fifth predetermined threshold.

[0090] As an example, the second channel state information includes at least one of a signal to interference and noise ratio (SINR), a reference signal received power (RSRP), a reference signal received quality (RSRQ), and a reference signal received strength (RSRI) of the sidelink.

[0091] As an example, the processing unit 101 may be configured to determine that the user equipment (UE) is to participate in federated learning non-independently when it is determined based on the second channel state information that there are other user equipments (AEs) that meet the following conditions: via the side links corresponding to the other user equipments, the user equipment can transmit model data related to the segmented model corresponding to the user equipment to the other user equipments within a first predetermined time range, and the other user equipments can transmit model data related to the segmented model corresponding to the other user equipments to the user equipment within a second predetermined time range. For example, the model data related to the segmented model corresponding to the UE may be the intermediate data #1 described in conjunction with FIG3, and the model data related to the segmented model corresponding to the AE may be the intermediate data #2 described in conjunction with FIG3.

[0092] As an example, the processing unit 101 can be configured to determine that the user device is to independently participate in federated learning when it is determined based on the second channel state information that there are no other user devices that meet the following conditions: via the side links corresponding to the other user devices, the user device can transmit model data related to the segmented model corresponding to the user device to the other user devices within a first predetermined time range, and the other user devices can transmit model data related to the segmented model corresponding to the other user devices to the user device within a second predetermined time range.

[0093] As an example, the processing unit 101 may be configured to, when determining that a user equipment (UE) is to participate in federated learning non-independently and selecting a user equipment (AE) to be coordinated with the user equipment for training, send information related to federated learning to the user equipment and the coordinated user equipment. For example, the information related to federated learning includes a model to be trained and a split point of the model to be trained.

[0094] As an example, the processing unit 101 can be configured to broadcast the model to be trained and the segmentation points for segmenting the model to be trained to obtain the segmented model to the user equipment and the user equipment to be cooperated. For example, the electronic device 100 broadcasts the global model (e.g., the initial global model and the updated global model) and its segmentation points to the UE and AE in the Non-Standalone Member. In this case, both the UE and the AE have a complete global model and only need to perform local training and update on the corresponding parts of the global model according to the segmentation points.

[0095] As an example, the processing unit 101 may be configured to send a segmented model corresponding to the user equipment to the user equipment, and to send a segmented model corresponding to the user equipment to be coordinated to the user equipment to be coordinated. The global model may also be sent in a point-to-point manner, that is, the electronic device 100 may separately allocate downlink resources to the UE and AE for sending the corresponding segmented global model.

[0096] As an example, the processing unit 101 can be configured to notify the user equipment (UE) and the user equipment (AE) to be cooperated to report their trained segmented models respectively, and the electronic device 100 splices the trained segmented models to obtain a trained complete model. For example, in conjunction with Figure 3, after the UE and AE in the Non-Standalone Member complete the segmentation learning, the trained UE model is uploaded by the UE to the electronic device 100 and the trained AE model is uploaded by the AE to the electronic device 100, and spliced ​​at the electronic device 100 to obtain a trained complete model.

[0097] As an example, the processing unit 101 can be configured to notify the user equipment or the user equipment to be cooperated to splice the trained segmented models to obtain the trained complete model, and report the trained complete model to the electronic device 100. For example, after the UE and AE in the Non-Standalone Member complete the segmentation learning, one of the UE and the AE completes the splicing of the trained segmented models and uploads it to the electronic device 100. For example, the AE transmits the trained AE model to the UE via the sidelink, and the UE uploads the trained complete model to the electronic device 100 after completing the splicing of the trained UE model and the trained AE model. In addition, for example, the UE transmits the trained UE model to the AE via the sidelink, and the AE uploads the trained complete model to the electronic device 100 after completing the splicing of the trained UE model and the trained AE model.

[0098] As an example, the processing unit 101 may be configured to notify the user equipment and the user equipment to be coordinated of information about the side link between the user equipment and the user equipment to be coordinated.

[0099] FIG5 is a diagram illustrating a structural example of a federated learning network according to an embodiment of the present disclosure.

[0100] Figure 5 shows an example of the structure of a federated learning network using the vehicle-to-everything (V2X) network as an example. As shown in Figure 5, in this distributed network, multiple members perform federated learning training together with the electronic device 100.

[0101] In FIG5 , some Members may consist of only a single UE (for example, Member#i consists only of UE#i). Such a Member is a Standalone Member. In this case, the complete model to be trained is trained at the UE.

[0102] In Figure 5, some Members can be composed of a single UE and its nearby AEs. Such Members are Non-Standalone Members. In this case, the complete model to be trained (i.e., the complete model) is divided between the UE and the AE, for example, it is split into a UE model and an AE model. For example, Member#1 consists of UE#1 and AE#1, and the complete model to be trained is split into a UE#1 model corresponding to UE#1 (the left part of the complete model) and an AE#1 model corresponding to AE#1 (the right part of the complete model). The UE#1 model and the AE#1 model are spliced ​​to form the complete model to be trained. For example, Member#k consists of UE#k and AE#k, and the complete model to be trained is split into a UE#k model corresponding to UE#k (the left part of the complete model) and an AE#k model corresponding to AE#k (the right part of the complete model). The UE#k model and the AE#k model are spliced ​​to form the complete model to be trained. In addition, for different Non-Standalone Members, the split point between the UE model and the AE model may be different. For example, referring to FIG. 4 , the split point corresponding to Member#1 is at m=2, and the split point corresponding to Member#k is at m=3.

[0103] Before the start of federated learning training, the devices in the network (for example, devices that can participate in federated learning as UE or AE) report their own status information to the electronic device 100. By way of example and not limitation, the electronic device 100 can perform at least some of the following operations based on the status information uploaded by each device: 1). Select the UE (determine whether the UE participates in federated learning); 2). If it is determined that the UE participates in federated learning, decide whether the UE participates in federated learning as a Standalone Member or as a Non-Standalone Member; 3). If the UE participates in federated learning as a Non-Standalone Member, it is necessary to select the AE to cooperate with it and determine the split point of the model to be trained; 4). Allocate uplink transmission resources to the Standalone Member, and allocate uplink transmission resources and sidelink transmission resources to the UE and AE in the Non-Standalone Member, and decide how to upload the trained UE model and the trained AE model to the electronic device 100. During the training process of federated learning, 1)-4) may be performed again, that is, reselection of the UE, etc.

[0104] The following briefly describes an example of the training process of the federated learning network in Figure 5. 1). The electronic device 100 initializes the global model parameters and sends down the global model. 2). The Standalone Member that receives the global model performs training updates on the local model based on local data, and uploads the updated local model to the electronic device 100 after completion. For the Non-Standalone Member, the local model is trained and updated based on the local data of the UE (split learning is performed between the UE and the AE, and intermediate data is transmitted between each other through the side link). After completion, the updated local model is uploaded to the electronic device 100. 3). After receiving the local models uploaded by all Members, the electronic device 100 aggregates the global model and sends the aggregated global model to each Member. 4). Repeat 2)-3) several times until the trained global model converges.

[0105] The present disclosure further provides an electronic device for wireless communication according to another embodiment. FIG6 shows a functional module block diagram of an electronic device 600 for wireless communication according to another embodiment of the present disclosure.

[0106] As shown in Figure 6, the electronic device 600 includes: a communication unit 601, which can report the electronic device 600's own status information to the network side device that provides services for the electronic device 600, so that the network side device can determine whether the electronic device 600 should cooperate with other electronic devices to train the segmented model obtained by segmenting the model to be trained, thereby participating in federated learning non-independently, or independently train the model to be trained, thereby independently participating in federated learning.

[0107] The communication unit 601 may be implemented by one or more processing circuits, which may be implemented as a chip, for example.

[0108] The electronic device 600 can be, for example, arranged on the user equipment (UE) side or communicatively connected to the user equipment. It should also be noted here that the electronic device 600 can be implemented at the chip level, or it can also be implemented at the device level. For example, the electronic device 600 can work as the user equipment itself, and can also include external devices such as memory, transceiver (not shown in the figure), etc. The memory can be used to store programs and related data information that the user equipment needs to execute to implement various functions. The transceiver may include one or more communication interfaces to support communication with different devices (for example, base stations, other user equipment, etc.), and the implementation form of the transceiver is not specifically limited here.

[0109] As an example, the network side device may be the electronic device 100 mentioned above. As an example, the electronic device 600 may be the UE involved in the embodiment of the electronic device 100 above, and the other electronic devices to be coordinated with the electronic device 600 may be the AE involved in the embodiment of the electronic device 100 above.

[0110] The wireless communication system according to the present disclosure may be a 5G NR communication system. Furthermore, the wireless communication system according to the present disclosure may include a non-terrestrial network. Alternatively, the wireless communication system according to the present disclosure may also include a terrestrial network. Furthermore, those skilled in the art will appreciate that the wireless communication system according to the present disclosure may also be a 4G or 3G communication system.

[0111] For example, the electronic device 600 estimates its own state information Info U And report it to the network side device.

[0112] For details about federated learning, models to be trained, segmented learning, etc., please refer to the description in conjunction with Figures 2 and 3 in the embodiment of the electronic device 100, which will not be repeated here.

[0113] The electronic device 600 can act as a Standalone Member. In this case, the electronic device 600 does not participate in segmented learning, but independently trains the complete model to be trained locally. The trained local model is aggregated with the trained local models of other Members to perform global model aggregation for federated learning. Alternatively, the electronic device 600 can form a Non-Standalone Member with the AE to perform segmented learning on the model to be trained locally, and the trained local model of the Non-Standalone Member is aggregated with the trained local models of other Members to perform global model aggregation for federated learning.

[0114] In an embodiment of the present disclosure, an electronic device 600 reports its own state information to a network device, allowing the network device to determine whether the electronic device 600 should participate in federated learning independently or independently, enabling more efficient federated learning. For example, the computing or communication capabilities of different electronic devices participating in federated learning are heterogeneous. Some electronic devices carry important data but lack computing or communication capabilities, while some electronic devices have strong computing and communication capabilities. For example, for electronic devices with insufficient computing or communication capabilities, the burden on the electronic devices during the federated learning process can be reduced by cooperating with other electronic devices to train the segmented model; electronic devices with strong computing and communication capabilities can complete the training of the model to be trained locally without cooperating with other electronic devices. In addition, the computing or communication resources of other electronic devices in the communication network can be fully utilized. In addition, the number of users participating in federated learning that the network device can support is generally limited, so electronic devices need to be selected before the start of federated learning. Some devices that are not selected but still wish to participate in federated learning (and contribute to federated learning) can participate in training as other electronic devices. For Non-Standalone Member, other electronic devices only have part of the model parameters of the model to be trained. The intermediate data is transmitted between the electronic device and other electronic devices, which ensures the privacy and security of the data. That is, data privacy protection is further improved.

[0115] As an example, the state information of the electronic device 600 includes first channel state information of a link between the electronic device 600 and a network-side device.

[0116] As an example, the first channel state information includes at least one of the signal-to-interference and noise ratio (SINR), reference signal received power (RSRP), reference signal received quality (RSRQ), and reference signal received intensity (RSRI) of the uplink between the electronic device 600 and the network side device.

[0117] As an example, the self-state information of the electronic device 600 includes computing and storage capability information of the electronic device 600 .

[0118] As an example, the computing and storage capability information includes at least one of a CPU occupancy rate and a memory size of the electronic device 600 .

[0119] As an example, the self-state information of the electronic device 600 includes local data information of the electronic device 600 .

[0120] As an example, the local data information includes the number of training samples and sample dimensions that the electronic device 600 will use when independently participating in federated learning.

[0121] As an example, the state information of the electronic device 600 includes the power level information of the electronic device 600 .

[0122] As an example, the state information of the electronic device 600 includes the location information of the electronic device 600 .

[0123] As an example, the self-state information of the electronic device 600 includes movement information of the electronic device 600 .

[0124] As an example, the movement information includes at least one of the movement speed, the movement direction, and the stay time of the electronic device 600 .

[0125] As an example, the state information of the electronic device 600 includes second channel state information of a side link between the electronic device 600 and other electronic devices within a predetermined range of the electronic device 600 .

[0126] For a description of how the network-side device determines whether the electronic device 600 is to participate in federated learning non-independently or independently based on the status information reported by the electronic device 600, please refer to the relevant description in the embodiment of the electronic device 100, which will not be repeated here.

[0127] As an example, the communication unit 601 can be configured to perform the following operations on the first segmented model corresponding to the electronic device 600 a predetermined number of times in each round of global training of the federated learning in the case of non-independent participation in federated learning to obtain the trained first segmented model: transmitting the first data obtained by training the first segmented model to the cooperating electronic device that performs cooperative training with the electronic device 600, and updating the first segmented model based on the second data received from the cooperating electronic device, wherein the second data is obtained by the cooperating electronic device training the second segmented model corresponding to it based on the first data. As an example, the electronic device 600 can be the UE described in conjunction with Figure 3, the first segmented model can be the UE model described in conjunction with Figure 3, the cooperating electronic device can be the AE described in conjunction with Figure 3, the first data can be the intermediate data #1 described in conjunction with Figure 3, the second data can be the intermediate data #2 described in conjunction with Figure 3, and the second segmented model can be the AE model described in conjunction with Figure 3.

[0128] As an example, the communication unit 601 can be configured to report the trained first segmented model to the network side device, so that the network side device can splice the trained first segmented model and the trained second segmented model received from the cooperating electronic device to obtain a trained complete model, wherein the trained second segmented model is obtained by the cooperating electronic device training the second segmented model in the global training. In conjunction with Figure 3, after the electronic device 600 and the cooperating electronic device complete the segmentation learning, the trained UE model is uploaded by the electronic device 600 to the network side device and the trained AE model is uploaded by the cooperating electronic device to the network side device, and spliced ​​at the network side device to obtain the trained complete model.

[0129] As an example, the communication unit 601 can be configured to splice the trained first segmented model and the trained second segmented model to obtain a trained complete model, and report the trained complete model to the network side device, wherein the trained second segmented model is obtained by training the second segmented model in the global training by the cooperating electronic device. In conjunction with Figure 3, the AE transmits the trained AE model to the electronic device 600 via the sidelink, and the electronic device 600 completes the splicing of the trained UE model and the trained AE model and uploads the trained complete model to the network side device.

[0130] The present disclosure further provides an electronic device for wireless communication according to yet another embodiment. FIG7 shows a functional module block diagram of an electronic device 700 for wireless communication according to yet another embodiment of the present disclosure.

[0131] As shown in Figure 7, the electronic device 700 includes: a reporting unit 701, which can report the status information of the electronic device 700 to the network side device that provides services for the electronic device 700, so that the network side device can determine whether the electronic device 700 can cooperate with other electronic devices to train the segmented model obtained by segmenting the model to be trained in federated learning, so that other electronic devices participate in federated learning non-independently, or whether other electronic devices need to independently train the model to be trained and thus independently participate in federated learning.

[0132] The reporting unit 701 may be implemented by one or more processing circuits, which may be implemented as a chip, for example.

[0133] The electronic device 700 can, for example, be arranged on the user equipment side or be communicatively connected to the user equipment. Here, it should also be noted that the electronic device 700 can be implemented at the chip level, or it can also be implemented at the device level. For example, the electronic device 700 can work as the user equipment itself, and can also include external devices such as memory, transceiver (not shown in the figure), etc. The memory can be used to store programs and related data information that need to be executed by the user equipment to implement various functions. The transceiver may include one or more communication interfaces to support communication with different devices (for example, base stations, other user equipment, etc.), and the implementation form of the transceiver is not specifically limited here.

[0134] As an example, the network side device may be the electronic device 100 mentioned above. As an example, the electronic device 700 may be the AE involved in the above embodiment of the electronic device 100, and the other electronic device to be coordinated with the electronic device 700 may be the UE involved in the above embodiment of the electronic device 100.

[0135] The wireless communication system according to the present disclosure may be a 5G NR communication system. Furthermore, the wireless communication system according to the present disclosure may include a non-terrestrial network. Alternatively, the wireless communication system according to the present disclosure may also include a terrestrial network. Furthermore, those skilled in the art will appreciate that the wireless communication system according to the present disclosure may also be a 4G or 3G communication system.

[0136] For example, the electronic device 700 estimates its own state information Info A And report it to the network side device.

[0137] For details about federated learning, models to be trained, segmented learning, etc., please refer to the description in conjunction with Figures 2 and 3 in the embodiment of the electronic device 100, which will not be repeated here.

[0138] The electronic device 700 and other electronic devices (UE) form a Non-Standalone Member to perform segmented learning on the model to be trained locally, and the trained local model of the Non-Standalone Member and the trained local models of other Members jointly perform global model aggregation to perform federated learning.

[0139] In an embodiment of the present disclosure, the electronic device 700 reports its own status information to the network-side device so that the network-side device can determine whether other electronic devices should participate in federated learning non-independently or independently, so that federated learning can be performed more efficiently. For example, the computing or communication resources of the electronic device 700 can be fully utilized. In addition, for the Non-Standalone Member in federated learning, the electronic device 700 only has part of the model parameters of the model to be trained, and the intermediate data is transmitted between the electronic device 700 and other electronic devices, which ensures the privacy and security of the data, that is, the data privacy protection is further improved.

[0140] As an example, the state information of the electronic device 700 includes third channel state information of the link between the electronic device 700 and the network-side device.

[0141] As an example, the third channel state information includes at least one of the signal-to-interference and noise ratio (SINR), reference signal received power (RSRP), reference signal received quality (RSRQ), and reference signal received intensity (RSRI) of the uplink between the electronic device 700 and the network side device.

[0142] As an example, the self-state information of the electronic device 700 includes computing and storage capability information of the electronic device 700 .

[0143] As an example, the computing and storage capability information includes at least one of a CPU occupancy rate and a memory size of the electronic device 700 .

[0144] As an example, the self-state information of the electronic device 700 includes local data information of the electronic device 700 .

[0145] As an example, the local data information includes the number of training samples and sample dimensions that the electronic device 700 will use when independently participating in federated learning.

[0146] As an example, the state information of the electronic device 700 includes the power level information of the electronic device 700 .

[0147] As an example, the self-state information of the electronic device 700 includes the location information of the electronic device 700 .

[0148] As an example, the self-state information of the electronic device 700 includes movement information of the electronic device 700 .

[0149] As an example, the movement information includes at least one of the movement speed, the movement direction, and the stay time of the electronic device 700 .

[0150] As an example, the state information of the electronic device 700 includes fourth channel state information of a side link between the electronic device 700 and other electronic devices within a predetermined range of the electronic device 700 .

[0151] As an example, the reporting unit 701 can be configured to perform the following operations on the second segmented model corresponding to the electronic device 700 a predetermined number of times in each round of global training of the federated learning in a case where other electronic devices participate in the federated learning non-independently, thereby obtaining a trained second segmented model: receiving first data obtained by training the first segmented model corresponding to the other electronic devices from the other electronic devices, and training the second segmented model based on the first data to obtain second data, and transmitting the second data to the other electronic devices for the other electronic devices to update the first segmented model. As an example, the other electronic device can be the UE described in conjunction with FIG3, the first segmented model can be the UE model described in conjunction with FIG3, the first data can be the intermediate data #1 described in conjunction with FIG3, the electronic device 700 can be the AE described in conjunction with FIG3, the second segmented model can be the AE model described in conjunction with FIG3, and the second data can be the intermediate data #2 described in conjunction with FIG3.

[0152] As an example, the reporting unit 701 can be configured to report the trained second segmented model to the network side device, so that the network side device can splice the trained second segmented model with the trained first segmented model received from other electronic devices to obtain a trained complete model, wherein the trained first segmented model is obtained by other electronic devices training the first segmented model in global training. In conjunction with Figure 3, after the electronic device 700 and other electronic devices complete the segmentation learning, the trained AE model is uploaded by the electronic device 700 to the network side device and the trained UE model is uploaded by other electronic devices to the network side device, and spliced ​​at the network side device to obtain a trained complete model.

[0153] As an example, the reporting unit 701 can be configured to splice the trained second segmented model and the trained first segmented model to obtain a trained complete model, and report the trained complete model to the network side device, wherein the trained first segmented model is obtained by other electronic devices training the first segmented model in global training. In conjunction with Figure 3, the UE transmits the trained UE model to the electronic device 700 via the sidelink, and the electronic device 700 completes the splicing of the trained UE model and the trained AE model and uploads the trained complete model to the network side device.

[0154] The present disclosure also provides a wireless communication system according to an embodiment, including: electronic device 100, electronic device 600, and electronic device 700. In the wireless communication system, referring to FIG5 , electronic device 100 can serve as a base station, electronic device 600 can serve as a UE, and electronic device 700 can serve as an AE.

[0155] In the process of describing the electronic device for wireless communication in the above embodiments, it is obvious that some processes or methods are also disclosed. Below, an overview of these methods is given without repeating some of the details discussed above, but it should be noted that although these methods are disclosed in the process of describing the electronic device for wireless communication, these methods do not necessarily use the components described or are not necessarily performed by those components. For example, the embodiments of the electronic device for wireless communication can be partially or completely implemented using hardware and / or firmware, and the methods for wireless communication discussed below can be completely implemented by computer-executable programs, although these methods can also use the hardware and / or firmware of the electronic device for wireless communication.

[0156] Figure 8 shows a flowchart of a method S800 for wireless communication according to one embodiment of the present disclosure. Method S800 begins at step S802. At step S804, based on the state information reported by user devices within the service range of the electronic device, it is determined whether the user device should cooperate with other user devices to train a segmented model obtained by segmenting the model to be trained, thereby participating in federated learning non-independently, or whether the user device should independently train the model to be trained, thereby participating in federated learning independently. Method S800 ends at step S806.

[0157] The method may be executed, for example, by the electronic device 100 described above. For specific details, please refer to the description of the related processing of the electronic device 100, which will not be repeated here.

[0158] Figure 9 shows a flowchart of a method S900 for wireless communication according to another embodiment of the present disclosure. Method S900 begins at step S902. At step S904, the electronic device's own state information is reported to a network device providing services for the electronic device, so that the network device can determine whether the electronic device should cooperate with other electronic devices to train a segmented model obtained by segmenting the model to be trained, thereby participating in federated learning non-independently, or whether the electronic device should independently train the model to be trained, thereby participating in federated learning independently. Method S900 ends at step S906.

[0159] The method may be executed, for example, by the electronic device 600 described above. For specific details, please refer to the description of the related processing of the electronic device 600, which will not be repeated here.

[0160] FIG10 shows a flowchart of a method S1000 for wireless communication according to another embodiment of the present disclosure. Method S1000 begins at step S1002. At step S1004, the electronic device's own status information is reported to a network device providing services for the electronic device, so that the network device can determine whether the electronic device can cooperate with other electronic devices in federated learning to train a segmented model obtained by segmenting the model to be trained, thereby allowing other electronic devices to participate in federated learning non-independently, or whether other electronic devices need to independently train the model to be trained and thereby independently participate in federated learning. Method S1000 ends at step S1006.

[0161] The method may be executed, for example, by the electronic device 700 described above. For specific details, please refer to the description of the related processing of the electronic device 700, which will not be repeated here.

[0162] The technology of the present disclosure can be applied to various products.

[0163] The electronic device 100 can be implemented as various network-side devices such as a base station. The base station can be implemented as any type of evolved Node B (eNB) or gNB (5G base station). eNBs include, for example, macro eNBs and small eNBs. Small eNBs can be eNBs that cover cells smaller than macro cells, such as pico eNBs, micro eNBs, and home (femto) eNBs. Similar situations can also apply to gNBs. Alternatively, the base station can be implemented as any other type of base station, such as a NodeB and a base transceiver station (BTS). The base station may include: a main body (also referred to as a base station device) configured to control wireless communications; and one or more remote radio heads (RRHs) located at a different location from the main body. In addition, various types of electronic devices can work as base stations by temporarily or semi-permanently performing base station functions.

[0164] The electronic devices 600 and 700 may be implemented as various user devices. The user devices may be implemented as mobile terminals (such as smartphones, tablet personal computers (PCs), notebook PCs, portable gaming terminals, portable / dongle-type mobile routers, and digital camera devices) or vehicle-mounted terminals (such as car navigation devices). The user devices may also be implemented as terminals that perform machine-to-machine (M2M) communication (also known as machine-type communication (MTC) terminals). In addition, the user devices may be wireless communication modules (such as integrated circuit modules comprising a single chip) installed on each of the above-mentioned terminals.

[0165] [Application examples for base stations]

[0166] (First application example)

[0167] Figure 11 is a block diagram illustrating a first example of a schematic configuration of an eNB or gNB to which the techniques of this disclosure can be applied. Note that the following description uses an eNB as an example, but is equally applicable to gNBs. An eNB 800 includes one or more antennas 810 and a base station device 820. The base station device 820 and each antenna 810 can be connected to each other via an RF cable.

[0168] Each of the antennas 810 includes a single or multiple antenna elements (such as multiple antenna elements included in a multiple-input multiple-output (MIMO) antenna) and is used for base station device 820 to transmit and receive wireless signals. As shown in FIG11 , eNB 800 may include multiple antennas 810. For example, multiple antennas 810 may be compatible with multiple frequency bands used by eNB 800. Although FIG11 shows an example in which eNB 800 includes multiple antennas 810, eNB 800 may also include a single antenna 810.

[0169] The base station device 820 includes a controller 821 , a memory 822 , a network interface 823 , and a wireless communication interface 825 .

[0170] The controller 821 may be, for example, a CPU or a DSP, and operates various functions of the higher layers of the base station device 820. For example, the controller 821 generates data packets based on the data in the signal processed by the wireless communication interface 825, and transmits the generated packets via the network interface 823. The controller 821 may bundle data from multiple baseband processors to generate bundled packets, and transmit the generated bundled packets. The controller 821 may have logic functions for performing the following controls: the control may be radio resource control, radio bearer control, mobility management, admission control, and scheduling. The control may be performed in conjunction with a nearby eNB or core network node. The memory 822 includes RAM and ROM, and stores programs executed by the controller 821 and various types of control data (such as a terminal list, transmission power data, and scheduling data).

[0171] The network interface 823 is a communication interface for connecting the base station device 820 to the core network 824. The controller 821 can communicate with the core network node or another eNB via the network interface 823. In this case, the eNB 800 and the core network node or other eNBs can be connected to each other through a logical interface (such as an S1 interface and an X2 interface). The network interface 823 can also be a wired communication interface or a wireless communication interface for a wireless backhaul line. If the network interface 823 is a wireless communication interface, the network interface 823 can use a higher frequency band for wireless communication than the frequency band used by the wireless communication interface 825.

[0172] The wireless communication interface 825 supports any cellular communication scheme, such as Long Term Evolution (LTE) and LTE-Advanced, and provides wireless connectivity to terminals located in the cell of the eNB 800 via the antenna 810. The wireless communication interface 825 may typically include, for example, a baseband (BB) processor 826 and RF circuitry 87. The BB processor 826 can perform various signal processing functions, such as encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and layers such as Layer 1, Medium Access Control (MAC), Radio Link Control (RLC), and Packet Data Convergence Protocol (PDCP). In place of the controller 821, the BB processor 826 may have some or all of the aforementioned logical functions. The BB processor 826 may be a memory that stores communication control programs, or a module including a processor configured to execute programs and associated circuitry. Program updates can modify the functionality of the BB processor 826. This module may be a card or blade inserted into a slot in the base station device 820. Alternatively, the module may be a chip mounted on the card or blade. Meanwhile, the RF circuit 87 may include, for example, a mixer, a filter, and an amplifier, and transmits and receives wireless signals via the antenna 810 .

[0173] As shown in FIG11 , the wireless communication interface 825 may include multiple BB processors 826. For example, multiple BB processors 826 may be compatible with multiple frequency bands used by the eNB 800. As shown in FIG11 , the wireless communication interface 825 may include multiple RF circuits 87. For example, multiple RF circuits 87 may be compatible with multiple antenna elements. Although FIG11 illustrates an example in which the wireless communication interface 825 includes multiple BB processors 826 and multiple RF circuits 87, the wireless communication interface 825 may also include a single BB processor 826 or a single RF circuit 87.

[0174] In the eNB 800 shown in FIG11 , when the electronic device 100 is implemented as a base station, its transceiver may be implemented by the wireless communication interface 825. At least part of the functions may also be implemented by the controller 821. For example, the controller 821 may enable more efficient federated learning by executing the functions of the units in the electronic device 100.

[0175] (Second application example)

[0176] FIG12 is a block diagram illustrating a second example of a schematic configuration of an eNB or gNB to which the techniques of this disclosure can be applied. Note that similarly, the following description uses an eNB as an example, but is equally applicable to a gNB. An eNB 830 includes one or more antennas 840, a base station device 850, and an RRH 860. The RRH 860 and each antenna 840 can be connected to each other via an RF cable. The base station device 850 and the RRH 860 can be connected to each other via a high-speed line such as an optical fiber cable.

[0177] Each of the antennas 840 includes a single or multiple antenna elements (such as multiple antenna elements included in a MIMO antenna) and is used for RRH 860 to transmit and receive wireless signals. As shown in FIG12 , eNB 830 may include multiple antennas 840. For example, multiple antennas 840 may be compatible with multiple frequency bands used by eNB 830. Although FIG12 shows an example in which eNB 830 includes multiple antennas 840, eNB 830 may also include a single antenna 840.

[0178] Base station device 850 includes a controller 851, a memory 852, a network interface 853, a wireless communication interface 855, and a connection interface 857. Controller 851, memory 852, and network interface 853 are the same as controller 821, memory 822, and network interface 823 described with reference to FIG.

[0179] The wireless communication interface 855 supports any cellular communication scheme (such as LTE and LTE-Advanced) and provides wireless communication to terminals located in the sector corresponding to the RRH 860 via the RRH 860 and the antenna 840. The wireless communication interface 855 may generally include, for example, a BB processor 856. The BB processor 856 is the same as the BB processor 826 described with reference to FIG. 11, except that the BB processor 856 is connected to the RF circuit 864 of the RRH 860 via the connection interface 857. As shown in FIG. 12, the wireless communication interface 855 may include multiple BB processors 856. For example, the multiple BB processors 856 may be compatible with multiple frequency bands used by the eNB 830. Although FIG. 12 shows an example in which the wireless communication interface 855 includes multiple BB processors 856, the wireless communication interface 855 may also include a single BB processor 856.

[0180] The connection interface 857 is an interface for connecting the base station device 850 (wireless communication interface 855) to the RRH 860. The connection interface 857 may also be a communication module for connecting the base station device 850 (wireless communication interface 855) to the RRH 860 for communication in the high-speed line.

[0181] The RRH 860 includes a connection interface 861 and a wireless communication interface 863 .

[0182] The connection interface 861 is an interface for connecting the RRH 860 (wireless communication interface 863) to the base station device 850. The connection interface 861 may also be a communication module for communication in the above-mentioned high-speed line.

[0183] The wireless communication interface 863 transmits and receives wireless signals via the antenna 840. The wireless communication interface 863 may generally include, for example, an RF circuit 864. The RF circuit 864 may include, for example, a mixer, a filter, and an amplifier, and transmits and receives wireless signals via the antenna 840. As shown in FIG12 , the wireless communication interface 863 may include multiple RF circuits 864. For example, the multiple RF circuits 864 may support multiple antenna elements. Although FIG12 shows an example in which the wireless communication interface 863 includes multiple RF circuits 864, the wireless communication interface 863 may also include a single RF circuit 864.

[0184] In the eNB 830 shown in FIG12 , when the electronic device 100 is implemented as a base station, its transceiver may be implemented by the wireless communication interface 855. At least part of the functions may also be implemented by the controller 851. For example, the controller 851 may enable more efficient federated learning by executing the functions of the units in the electronic device 100.

[0185] [Application examples on user devices]

[0186] (First application example)

[0187] 13 is a block diagram showing an example of a schematic configuration of a smartphone 900 to which the technology of the present disclosure can be applied. The smartphone 900 includes a processor 901, a memory 902, a storage device 903, an external connection interface 904, a camera 906, a sensor 907, a microphone 908, an input device 909, a display device 910, a speaker 911, a wireless communication interface 912, one or more antenna switches 915, one or more antennas 916, a bus 917, a battery 918, and an auxiliary controller 919.

[0188] The processor 901 may be, for example, a CPU or a system on a chip (SoC), and controls the functions of the application layer and other layers of the smartphone 900. The memory 902 includes RAM and ROM, and stores data and programs executed by the processor 901. The storage device 903 may include storage media such as semiconductor memories and hard disks. The external connection interface 904 is an interface for connecting external devices (such as memory cards and universal serial bus (USB) devices) to the smartphone 900.

[0189] The camera 906 includes an image sensor such as a charge coupled device (CCD) and a complementary metal oxide semiconductor (CMOS) and generates a captured image. The sensor 907 may include a group of sensors such as a measurement sensor, a gyroscope sensor, a geomagnetic sensor, and an acceleration sensor. The microphone 908 converts the sound input to the smartphone 900 into an audio signal. The input device 909 includes, for example, a touch sensor, a keypad, a keyboard, a button, or a switch configured to detect a touch on the screen of the display device 910, and receives an operation or information input from the user. The display device 910 includes a screen such as a liquid crystal display (LCD) and an organic light emitting diode (OLED) display and displays an output image of the smartphone 900. The speaker 911 converts the audio signal output from the smartphone 900 into sound.

[0190] The wireless communication interface 912 supports any cellular communication scheme (such as LTE and LTE-Advanced) and performs wireless communication. The wireless communication interface 912 may generally include, for example, a BB processor 913 and an RF circuit 914. The BB processor 913 may perform, for example, encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and may perform various types of signal processing for wireless communication. Meanwhile, the RF circuit 914 may include, for example, mixers, filters, and amplifiers, and transmit and receive wireless signals via an antenna 916. Note that while the figure shows a scenario where one RF link is connected to one antenna, this is merely illustrative, and also includes scenarios where one RF link is connected to multiple antennas via multiple phase shifters. The wireless communication interface 912 may be a chip module on which the BB processor 913 and the RF circuit 914 are integrated. As shown in FIG13 , the wireless communication interface 912 may include multiple BB processors 913 and multiple RF circuits 914. Although FIG. 13 illustrates an example in which the wireless communication interface 912 includes a plurality of BB processors 913 and a plurality of RF circuits 914 , the wireless communication interface 912 may also include a single BB processor 913 or a single RF circuit 914 .

[0191] In addition, in addition to the cellular communication scheme, the wireless communication interface 912 can support other types of wireless communication schemes, such as a short-range wireless communication scheme, a near-field communication scheme, and a wireless local area network (LAN) scheme. In this case, the wireless communication interface 912 may include a BB processor 913 and an RF circuit 914 for each wireless communication scheme.

[0192] Each of the antenna switches 915 switches a connection destination of the antenna 916 between a plurality of circuits (eg, circuits for different wireless communication schemes) included in the wireless communication interface 912 .

[0193] Each of the antennas 916 includes a single or multiple antenna elements (such as multiple antenna elements included in a MIMO antenna) and is used for transmitting and receiving wireless signals via the wireless communication interface 912. As shown in FIG13 , the smartphone 900 may include multiple antennas 916. Although FIG13 shows an example in which the smartphone 900 includes multiple antennas 916, the smartphone 900 may also include a single antenna 916.

[0194] In addition, the smartphone 900 may include an antenna 916 for each wireless communication scheme. In this case, the antenna switch 915 may be omitted from the configuration of the smartphone 900.

[0195] The bus 917 connects the processor 901, the memory 902, the storage device 903, the external connection interface 904, the camera 906, the sensor 907, the microphone 908, the input device 909, the display device 910, the speaker 911, the wireless communication interface 912, and the auxiliary controller 919. The battery 918 supplies power to the various blocks of the smartphone 900 shown in FIG13 via feeders, which are partially shown as dotted lines in the figure. The auxiliary controller 919 operates the minimum necessary functions of the smartphone 900, for example, in sleep mode.

[0196] In the smartphone 900 shown in FIG13 , when the electronic devices 600 and 700 are implemented as smartphones on the user device side, for example, the transceivers of the electronic devices 600 and 700 may be implemented by the wireless communication interface 912. At least a portion of the functions may also be implemented by the processor 901 or the auxiliary controller 919. For example, the processor 901 or the auxiliary controller 919 may enable more efficient federated learning by executing the functions of the units in the electronic devices 600 and 700 described above.

[0197] (Second application example)

[0198] 14 is a block diagram showing an example of a schematic configuration of a car navigation device 920 to which the technology of the present disclosure can be applied. The car navigation device 920 includes a processor 921, a memory 922, a global positioning system (GPS) module 924, a sensor 925, a data interface 926, a content player 97, a storage medium interface 928, an input device 99, a display device 930, a speaker 931, a wireless communication interface 913, one or more antenna switches 936, one or more antennas 937, and a battery 938.

[0199] The processor 921 may be, for example, a CPU or an SoC, and controls a navigation function and other functions of the car navigation apparatus 920. The memory 922 includes a RAM and a ROM, and stores data and programs executed by the processor 921.

[0200] The GPS module 924 measures the position (such as latitude, longitude, and altitude) of the car navigation device 920 using GPS signals received from GPS satellites. The sensor 925 may include a group of sensors such as a gyroscope sensor, a geomagnetic sensor, and an air pressure sensor. The data interface 926 is connected to, for example, the in-vehicle network 941 via an unillustrated terminal and acquires data generated by the vehicle (such as vehicle speed data).

[0201] The content player 97 reproduces content stored in a storage medium (such as a CD or DVD) inserted into the storage medium interface 928. The input device 99 includes, for example, a touch sensor, button, or switch configured to detect a touch on the screen of the display device 930, and receives operations or information input from the user. The display device 930 includes a screen such as an LCD or OLED display and displays images of the navigation function or reproduced content. The speaker 931 outputs sounds of the navigation function or reproduced content.

[0202] The wireless communication interface 913 supports any cellular communication scheme (such as LTE and LTE-Advanced) and performs wireless communication. The wireless communication interface 913 may generally include, for example, a BB processor 934 and an RF circuit 935. The BB processor 934 may perform, for example, encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and perform various types of signal processing for wireless communication. Meanwhile, the RF circuit 935 may include, for example, a mixer, a filter, and an amplifier, and transmit and receive wireless signals via an antenna 937. The wireless communication interface 913 may also be a chip module on which the BB processor 934 and the RF circuit 935 are integrated. As shown in Figure 14, the wireless communication interface 913 may include multiple BB processors 934 and multiple RF circuits 935. Although Figure 14 shows an example in which the wireless communication interface 913 includes multiple BB processors 934 and multiple RF circuits 935, the wireless communication interface 913 may also include a single BB processor 934 or a single RF circuit 935.

[0203] In addition, in addition to the cellular communication scheme, the wireless communication interface 913 can support other types of wireless communication schemes, such as a short-range wireless communication scheme, a near field communication scheme, and a wireless LAN scheme. In this case, for each wireless communication scheme, the wireless communication interface 913 can include a BB processor 934 and an RF circuit 935.

[0204] Each of the antenna switches 936 switches a connection destination of the antenna 937 between a plurality of circuits included in the wireless communication interface 913 , such as circuits for different wireless communication schemes.

[0205] Each of the antennas 937 includes a single or multiple antenna elements (such as multiple antenna elements included in a MIMO antenna) and is used for transmitting and receiving wireless signals via the wireless communication interface 913. As shown in FIG14, the car navigation device 920 may include multiple antennas 937. Although FIG14 shows an example in which the car navigation device 920 includes multiple antennas 937, the car navigation device 920 may also include a single antenna 937.

[0206] Furthermore, the car navigation device 920 may include an antenna 937 for each wireless communication scheme. In this case, the antenna switch 936 may be omitted from the configuration of the car navigation device 920.

[0207] The battery 938 supplies power to the respective blocks of the car navigation apparatus 920 shown in Fig. 14 via a feeder line, which is partially shown as a dotted line in the figure. The battery 938 accumulates the power supplied from the vehicle.

[0208] In the car navigation device 920 shown in FIG14 , when the electronic devices 600 and 700 are implemented as, for example, car navigation devices serving as user devices, the transceivers of the electronic devices 600 and 700 may be implemented by the wireless communication interface 933. At least a portion of the functions may also be implemented by the processor 921. For example, the processor 921 may enable more efficient federated learning by executing the functions of the units in the electronic devices 600 and 700 described above.

[0209] The technology of the present disclosure can also be implemented as an in-vehicle system (or vehicle) 940 including a car navigation device 920, an in-vehicle network 941, and one or more blocks of a vehicle module 942. The vehicle module 942 generates vehicle data (such as vehicle speed, engine speed, and fault information) and outputs the generated data to the in-vehicle network 941.

[0210] The basic principles of the present invention are described above in conjunction with specific embodiments. However, it should be pointed out that those skilled in the art will understand that all or any steps or components of the methods and devices of the present invention can be implemented in any computing device (including a processor, storage medium, etc.) or a network of computing devices in the form of hardware, firmware, software, or a combination thereof. This can be achieved by those skilled in the art using their basic circuit design knowledge or basic programming skills after reading the description of the present invention.

[0211] Furthermore, the present invention also provides a program product storing machine-readable instruction codes. When the instruction codes are read and executed by a machine, the method according to the embodiment of the present invention can be executed.

[0212] Accordingly, the storage medium for carrying the program product storing the machine-readable instruction code is also included in the disclosure of the present invention. The storage medium includes but is not limited to a floppy disk, an optical disk, a magneto-optical disk, a memory card, a memory stick, and the like.

[0213] When the present invention is implemented through software or firmware, the programs constituting the software are installed from a storage medium or a network to a computer with a dedicated hardware structure (such as the general-purpose computer 1500 shown in Figure 15). When various programs are installed on the computer, it can perform various functions, etc.

[0214] In FIG15 , a central processing unit (CPU) 1501 executes various processes according to a program stored in a read-only memory (ROM) 1502 or a program loaded from a storage section 1508 to a random access memory (RAM) 1503. In the RAM 1503, data required when the CPU 1501 executes various processes, etc., is also stored as needed. The CPU 1501, the ROM 1502, and the RAM 1503 are connected to each other via a bus 1504. An input / output interface 1505 is also connected to the bus 1504.

[0215] The following components are connected to the input / output interface 1505: an input section 1506 (including a keyboard, a mouse, etc.), an output section 1507 (including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and speakers, etc.), a storage section 1508 (including a hard disk, etc.), and a communication section 1509 (including a network interface card such as a LAN card, a modem, etc.). The communication section 1509 performs communication processing via a network such as the Internet. A drive 1510 may also be connected to the input / output interface 1505 as needed. A removable medium 1511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is installed in the drive 1510 as needed, so that a computer program read therefrom is installed in the storage section 1508 as needed.

[0216] In the case of realizing the above-described series of processing by software, a program constituting the software is installed from a network such as the Internet or a storage medium such as the removable medium 1511 .

[0217] It should be understood by those skilled in the art that such storage media is not limited to the removable medium 1511 shown in FIG15 , which stores the program therein and is distributed separately from the device to provide the program to the user. Examples of the removable medium 1511 include magnetic disks (including floppy disks (registered trademark)), optical disks (including compact disk read-only memories (CD-ROMs) and digital versatile disks (DVDs)), magneto-optical disks (including minidiscs (MDs) (registered trademark)), and semiconductor memories. Alternatively, the storage medium may be the ROM 1502, a hard disk included in the storage section 1508, or the like, in which the program is stored and distributed to the user together with the device containing them.

[0218] It should also be noted that in the apparatus, method, and system of the present invention, each component or step can be decomposed and / or recombined. Such decomposition and / or recombination should be considered equivalent solutions of the present invention. Furthermore, the steps of performing the above series of processes can naturally be performed in chronological order according to the order described, but do not necessarily need to be performed in chronological order. Certain steps can be performed in parallel or independently of each other.

[0219] Finally, it should be noted that the terms "comprises," "comprising," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. Furthermore, in the absence of further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0220] Although the embodiments of the present invention have been described in detail above with reference to the accompanying drawings, it should be understood that the embodiments described above are merely illustrative of the present invention and are not intended to limit the present invention. It will be apparent to those skilled in the art that various modifications and variations may be made to the embodiments described above without departing from the spirit and scope of the present invention. Therefore, the scope of the present invention is limited solely by the appended claims and their equivalents.

[0221] The present technology can also be implemented as follows.

[0222] Solution 1. An electronic device for wireless communication, comprising:

[0223] The processing circuit is configured to:

[0224] Based on the self-status information reported by the user device within the service range of the electronic device, it is determined that in federated learning, the user device should cooperate with other user devices to train the segmented model obtained by segmenting the model to be trained, thereby participating in the federated learning non-independently, or independently train the model to be trained, thereby participating in the federated learning independently.

[0225] Solution 2. The electronic device according to Solution 1, wherein:

[0226] The self-state information includes first channel state information of a link between the user equipment and the electronic device, and

[0227] The processing circuit is configured to, if a value of the first channel state information is less than a first predetermined threshold, determine that the user equipment is to participate in the federated learning non-independently.

[0228] Option 3. An electronic device according to Option 2, wherein the first channel state information includes at least one of a signal-to-interference-and-noise ratio (SINR), a reference signal received power (RSRP), a reference signal received quality (RSRQ), and a reference signal received strength (RSRI) of the uplink between the user equipment and the electronic device.

[0229] Solution 4. The electronic device according to Solution 1, wherein:

[0230] The self-state information includes the computing and storage capability information of the user equipment, and

[0231] The processing circuit is configured to determine that the user device is to participate in the federated learning non-independently when the storage space size indicated by the computing and storage capability information is smaller than the size of the model to be trained, and / or the computing power indicated by the computing and storage capability information is smaller than the computing power required to train the model to be trained.

[0232] Solution 5. An electronic device according to Solution 4, wherein the computing and storage capability information includes at least one of the CPU occupancy and memory size of the user device.

[0233] Solution 6. The electronic device according to Solution 1, wherein:

[0234] The self-state information includes local data information of the user equipment, and

[0235] The processing circuit is configured to determine that the user device is to participate in the federated learning non-independently when a training time required for the user device to train the model to be trained is greater than a second predetermined threshold, wherein the training time is obtained based on the local data information and the computing and storage capacity information of the user device.

[0236] Solution 7. An electronic device according to Solution 6, wherein the local data information includes the number of training samples and sample dimensions that the user device will use when independently participating in the federated learning.

[0237] Solution 8. The electronic device according to Solution 1, wherein:

[0238] The self-state information includes the power information of the user equipment, and

[0239] The processing circuit is configured to determine that the user equipment is to participate in the federated learning non-independently if the power level indicated by the power level information is less than a third predetermined threshold.

[0240] Solution 9. The electronic device according to Solution 1, wherein:

[0241] The self-state information includes the location information of the user equipment, and

[0242] The processing circuit is configured to determine that the user equipment is to independently participate in the federated learning if it is determined based on the location information that no other user equipment exists within a predetermined range of the user equipment.

[0243] Solution 10. The electronic device according to Solution 1, wherein:

[0244] The self-state information includes the movement information of the user equipment, and

[0245] The processing circuit is configured to, when it is determined based on the movement information that the user equipment has high mobility, determine that the user equipment is to independently participate in the federated learning.

[0246] Solution 11. The electronic device according to Solution 10, wherein the movement information includes at least one of a movement speed, a movement direction, and a dwell time of the user device.

[0247] Solution 12. The electronic device according to any one of Solutions 1 to 11, wherein:

[0248] The processing circuit is configured to, when determining that the user equipment is to participate in the federated learning non-independently, select a user equipment to be cooperated with the user equipment for training based on second channel state information of a side link between the user equipment and other user equipment within a predetermined range of the user equipment.

[0249] Solution 13. The electronic device according to Solution 12, wherein:

[0250] The processing circuit is configured to select the following other user equipment as the user equipment to be coordinated: a value of the second channel state information of the side link corresponding to the other user equipment is greater than a fourth predetermined threshold.

[0251] Solution 14. The electronic device according to Solution 13, wherein:

[0252] The second channel state information includes at least one of a signal to interference plus noise ratio (SINR), a reference signal received power (RSRP), a reference signal received quality (RSRQ), and a reference signal received strength (RSRI) of the sidelink.

[0253] Solution 15. The electronic device according to Solution 12, wherein:

[0254] The processing circuit is configured to select other user devices that meet the following conditions as the user devices to be cooperated based on the second channel state information: via the side link corresponding to the other user devices, the user devices can transmit model data related to the segmented model corresponding to the user devices to the other user devices within a first predetermined time range, and / or the other user devices can transmit model data related to the segmented model corresponding to the other user devices to the user devices within a second predetermined time range.

[0255] Solution 16. The electronic device according to any one of Solution 12 to Solution 15, wherein:

[0256] The processing circuit is configured to, when the user equipment to be cooperated is selected, determine, based on the second channel state information, segmentation points for segmenting the model to be trained to obtain the segmented model.

[0257] Solution 17. The electronic device according to Solution 16, wherein:

[0258] The processing circuit is configured to make the determined segmentation point satisfy the following conditions:

[0259] Via the side link between the user device and the user device to be coordinated, the user device can transmit model data related to the segmented model corresponding to the user device to be coordinated to the user device to be coordinated within a first predetermined time range, and / or the user device to be coordinated can transmit model data related to the segmented model corresponding to the user device to be coordinated to the user device within a second predetermined time range.

[0260] Solution 18. The electronic device according to Solution 1, wherein:

[0261] The own state information includes second channel state information of a side link between the user equipment and other user equipments within a predetermined range of the user equipment.

[0262] Solution 19. The electronic device according to Solution 18, wherein:

[0263] The processing circuit is configured to determine that the user equipment is to participate in the federated learning non-independently if there is other user equipment within the predetermined range whose second channel state information value is greater than a fifth predetermined threshold.

[0264] Solution 20. The electronic device according to Solution 19, wherein:

[0265] The processing circuit is configured to determine that the user equipment is to independently participate in the federated learning when the second channel state information corresponding to other user equipments within the predetermined range is less than or equal to the fifth predetermined threshold.

[0266] Option 21. An electronic device according to Option 19 or 20, wherein the second channel state information includes at least one of the signal to interference and noise ratio SINR, reference signal received power RSRP, reference signal received quality RSRQ, and reference signal received strength RSRI of the side link.

[0267] Solution 22. The electronic device according to Solution 18, wherein:

[0268] The processing circuit is configured to determine that the user device is to participate in the federated learning non-independently when it is determined based on the second channel state information that there are other user devices that meet the following conditions: via the side link corresponding to the other user device, the user device can transmit model data related to the segmented model corresponding to the user device to the other user device within a first predetermined time range, and the other user device can transmit model data related to the segmented model corresponding to the other user device to the user device within a second predetermined time range.

[0269] Solution 23. The electronic device according to Solution 18, wherein:

[0270] The processing circuit is configured to determine that the user device is to independently participate in the federated learning when it is determined based on the second channel state information that there are no other user devices that meet the following conditions: the user device can transmit model data related to the segmented model corresponding to the user device to the other user device within a first predetermined time range via a side link corresponding to the other user device, and the other user device can transmit model data related to the segmented model corresponding to the other user device to the user device within a second predetermined time range.

[0271] Solution 24. The electronic device according to any one of Solutions 1 to 23, wherein:

[0272] The processing circuit is configured to send information about the federated learning to the user device and the user device to be cooperated when it is determined that the user device is to participate in the federated learning non-independently and a user device to be cooperated with the user device for training is selected.

[0273] Solution 25. The electronic device according to Solution 24, wherein:

[0274] The processing circuit is configured to broadcast the model to be trained and segmentation points for segmenting the model to be trained to obtain the segmented model to the user equipment and the user equipment to be coordinated.

[0275] Option 26. An electronic device according to Option 24, wherein the processing circuit is configured to send the segmented model corresponding to the user device to the user device, and to send the segmented model corresponding to the user device to be coordinated to the user device to be coordinated.

[0276] Scheme 27. An electronic device according to any one of Schemes 24 to 26, wherein the processing circuit is configured to notify the user device and the user device to be cooperated to report their trained segmented models respectively, and the electronic device splices the trained segmented models to obtain a trained complete model.

[0277] Solution 28. An electronic device according to any one of Solutions 24 to 26, wherein the processing circuit is configured to notify the user device or the user device to be cooperated to splice the trained segmented model to obtain a trained complete model, and report the trained complete model to the electronic device.

[0278] Option 29. An electronic device according to any one of Options 24 to 28, wherein the processing circuit is configured to notify the user device and the user device to be coordinated of information about a side link between the user device and the user device to be coordinated.

[0279] Solution 30. An electronic device for wireless communication, comprising:

[0280] The processing circuit is configured to:

[0281] Report the self-status information of the electronic device to the network-side device providing services for the electronic device, so that the network-side device can determine whether, in federated learning, the electronic device should cooperate with other electronic devices to train the segmented model obtained by segmenting the model to be trained, thereby participating in the federated learning non-independently, or whether the electronic device should independently train the model to be trained, thereby participating in the federated learning independently.

[0282] Solution 31. The electronic device according to Solution 30, wherein:

[0283] The self-state information includes first channel state information of a link between the electronic device and the network-side device.

[0284] Solution 32. The electronic device according to Solution 31, wherein:

[0285] The first channel state information includes at least one of a signal to interference and noise ratio (SINR), a reference signal received power (RSRP), a reference signal received quality (RSRQ), and a reference signal received intensity (RSRI) of an uplink between the electronic device and the network side device.

[0286] Solution 33. The electronic device according to Solution 30, wherein:

[0287] The self-state information includes computing and storage capability information of the electronic device.

[0288] Solution 34. The electronic device according to Solution 33, wherein:

[0289] The computing and storage capability information includes at least one of a CPU occupancy rate and a memory size of the electronic device.

[0290] Solution 35. The electronic device according to Solution 30, wherein:

[0291] The self-state information includes local data information of the electronic device.

[0292] Solution 36. The electronic device according to Solution 35, wherein:

[0293] The local data information includes the number of training samples and sample dimensions that the electronic device will use when independently participating in the federated learning.

[0294] Solution 37. The electronic device according to Solution 30, wherein:

[0295] The self-state information includes power information of the electronic device.

[0296] Solution 38. The electronic device according to Solution 30, wherein:

[0297] The self-state information includes location information of the electronic device.

[0298] Solution 39. The electronic device according to Solution 30, wherein:

[0299] The self-state information includes movement information of the electronic device.

[0300] Solution 40. The electronic device according to Solution 39, wherein:

[0301] The movement information includes at least one of a moving speed, a moving direction, and a stay time of the electronic device.

[0302] Solution 41. The electronic device according to Solution 30, wherein:

[0303] The self-state information includes second channel state information of a side link between the electronic device and other electronic devices within a predetermined range of the electronic device.

[0304] Solution 42. The electronic device according to any one of Solutions 30 to 41, wherein:

[0305] The processing circuit is configured to, when participating in the federated learning non-independently, perform the following operations on the first segmented model corresponding to the electronic device a predetermined number of times in each round of global training of the federated learning to obtain a trained first segmented model:

[0306] transmitting first data obtained by training the first segmented model to an electronic device that cooperates with the electronic device for training, and

[0307] The first segmented model is updated based on second data received from the cooperating electronic device, wherein the second data is obtained by the cooperating electronic device training a second segmented model corresponding thereto based on the first data.

[0308] Solution 43. The electronic device according to Solution 42, wherein:

[0309] The processing circuit is configured to report the trained first segmented model to the network side device, so that the network side device can splice the trained first segmented model with the trained second segmented model received from the cooperative electronic device to obtain a trained complete model.

[0310] The trained second segmented model is obtained by the coordinated electronic device training the second segmented model in the global training.

[0311] Solution 44. The electronic device according to Solution 42, wherein the processing circuit is configured to concatenate the trained first segmented model and the trained second segmented model to obtain a trained complete model, and report the trained complete model to the network-side device.

[0312] The trained second segmented model is obtained by the coordinated electronic device training the second segmented model in the global training.

[0313] Solution 45. An electronic device for wireless communication, comprising:

[0314] The processing circuit is configured to:

[0315] Report the electronic device's own status information to the network-side device that provides services for the electronic device, so that the network-side device can determine, in federated learning, whether the electronic device can cooperate with other electronic devices to train the segmented model obtained by segmenting the model to be trained, so that the other electronic devices participate in the federated learning non-independently, or whether the other electronic devices need to independently train the model to be trained, thereby independently participating in the federated learning.

[0316] Solution 46. The electronic device according to Solution 45, wherein:

[0317] The self-state information includes third channel state information of the link between the electronic device and the network-side device.

[0318] Solution 47. The electronic device according to Solution 46, wherein:

[0319] The third channel state information includes at least one of a signal to interference and noise ratio (SINR), a reference signal received power (RSRP), a reference signal received quality (RSRQ), and a reference signal received intensity (RSRI) of an uplink between the electronic device and the network side device.

[0320] Solution 48. The electronic device according to Solution 45, wherein:

[0321] The self-state information includes computing and storage capability information of the electronic device.

[0322] Solution 49. The electronic device according to Solution 48, wherein:

[0323] The computing and storage capability information includes at least one of a CPU occupancy rate and a memory size of the electronic device.

[0324] Solution 50. The electronic device according to Solution 49, wherein:

[0325] The self-state information includes local data information of the electronic device.

[0326] Solution 51. The electronic device according to Solution 50, wherein:

[0327] The local data information includes the number of training samples and sample dimensions that the electronic device will use when independently participating in the federated learning.

[0328] Solution 52. The electronic device according to Solution 45, wherein:

[0329] The self-state information includes power information of the electronic device.

[0330] Solution 53. The electronic device according to Solution 45, wherein:

[0331] The self-state information includes location information of the electronic device.

[0332] Solution 54. The electronic device according to Solution 45, wherein:

[0333] The self-state information includes movement information of the electronic device.

[0334] Solution 55. The electronic device according to Solution 54, wherein:

[0335] The movement information includes at least one of a moving speed, a moving direction, and a stay time of the electronic device.

[0336] Solution 56. The electronic device according to Solution 45, wherein:

[0337] The own state information includes fourth channel state information of a side link between the electronic device and other electronic devices within a predetermined range of the electronic device.

[0338] Solution 57. The electronic device according to any one of Solutions 45 to 56, wherein:

[0339] The processing circuit is configured to, when the other electronic devices participate in the federated learning dependently, perform the following operations on the second segmented model corresponding to the electronic device a predetermined number of times in each round of global training of the federated learning to obtain a trained second segmented model:

[0340] receiving, from the other electronic device, first data obtained by training a first segmented model corresponding to the other electronic device, and

[0341] The second segmented model is trained based on the first data to obtain second data, and the second data is transmitted to the other electronic device so that the other electronic device updates the first segmented model.

[0342] Solution 58. The electronic device according to Solution 57, wherein:

[0343] The processing circuit is configured to report the trained second segmented model to the network side device, so that the network side device can splice the trained second segmented model with the trained first segmented model received from the other electronic device to obtain a trained complete model.

[0344] The trained first segmented model is obtained by training the first segmented model by the other electronic devices in the global training.

[0345] Solution 59. The electronic device according to Solution 57, wherein the processing circuit is configured to concatenate the trained second segmented model and the trained first segmented model to obtain a trained complete model, and report the trained complete model to the network-side device.

[0346] The trained first segmented model is obtained by training the first segmented model by the other electronic devices in the global training.

[0347] Solution 60. A wireless communication system comprising:

[0348] The electronic device according to any one of items 1 to 29,

[0349] The electronic device according to any one of items 30 to 44, and

[0350] An electronic device according to any one of items 45 to 59.

[0351] Solution 61. A method for wireless communication, comprising:

[0352] Based on the self-status information reported by user devices within the service range of the electronic device, it is determined that in federated learning, the user device should cooperate with other user devices to train the segmented model obtained by segmenting the model to be trained, thereby participating in the federated learning non-independently, or independently train the model to be trained, thereby participating in the federated learning independently.

[0353] Solution 62. A method for wireless communication, comprising:

[0354] Reporting the self-status information of the electronic device to a network-side device providing services for the electronic device, so that the network-side device can determine, in federated learning, whether the electronic device should cooperate with other electronic devices to train a segmented model obtained by segmenting the model to be trained, thereby participating in the federated learning non-independently, or whether the electronic device should independently train the model to be trained, thereby participating in the federated learning independently.

[0355] Solution 63. A method for wireless communication, comprising:

[0356] Report the self-status information of the electronic device to the network-side device providing services for the electronic device, so that the network-side device can determine, in federated learning, whether the electronic device can cooperate with other electronic devices to train the segmented model obtained by segmenting the model to be trained, so that the other electronic devices participate in the federated learning non-independently, or whether the other electronic devices need to independently train the model to be trained, thereby independently participating in the federated learning.

[0357] Solution 64. A computer-readable storage medium having computer-executable instructions stored thereon, which, when executed, performs the method for wireless communication according to any one of Solutions 61 to 63.

Claims

1. An electronic device for wireless communication, comprising: A processing circuit configured to: Based on the self - status information reported by a user equipment within the service range of the electronic device, determine whether, in federated learning, the user equipment is to cooperate with other user equipment to train a segmented model obtained by segmenting a model to be trained, and thus participate in the federated learning non - independently, or is to independently train the model to be trained, and thus participate in the federated learning independently.

2. The electronic device according to claim 1, wherein, The self - status information includes first channel status information of a link between the user equipment and the electronic device, and The processing circuit is configured to determine that the user equipment is to participate in the federated learning non - independently when the value of the first channel status information is less than a first predetermined threshold.

3. The electronic device according to claim 2, wherein The first channel status information includes at least one of a signal - to - interference - plus - noise ratio (SINR), a reference signal received power (RSRP), a reference signal received quality (RSRQ), and a reference signal received intensity (RSRI) of an uplink between the user equipment and the electronic device.

4. The electronic device according to claim 1, wherein, The self - status information includes the computing and storage capacity information of the user equipment, and The processing circuit is configured to determine that the user equipment is to participate in the federated learning non - independently when the storage space size indicated by the computing and storage capacity information is less than the size of the model to be trained, and / or the computing power indicated by the computing and storage capacity information is less than the computing power required to train the model to be trained.

5. The electronic device according to claim 4, wherein, The computing and storage capacity information includes at least one of a CPU occupancy rate and a memory size of the user equipment.

6. The electronic device according to claim 1, wherein, The self - status information includes the local data information of the user equipment, and The processing circuit is configured to determine that the user equipment is to participate in the federated learning non - independently when the training time required for the user equipment to train the model to be trained is greater than a second predetermined threshold, where the training time is obtained based on the local data information and the computing and storage capacity information of the user equipment.

7. The electronic device according to claim 6, wherein, The local data information includes the number of training samples and the sample dimension that the user equipment will use when participating in the federated learning independently.

8. The electronic device according to claim 1, wherein, The self - status information includes the power information of the user equipment, and The processing circuit is configured to determine that the user equipment is to participate in the federated learning non - independently when the power indicated by the power information is less than a third predetermined threshold.

9. The electronic device according to claim 1, wherein, The self - status information includes the location information of the user equipment, and The processing circuit is configured to determine that the user equipment is to participate in the federated learning independently when it is determined based on the location information that there are no other user equipment within a predetermined range of the user equipment.

10. The electronic device according to claim 1, wherein, the self-status information includes the movement information of the user equipment, and the processing circuit is configured to determine that the user equipment is to independently participate in the federated learning when it is determined based on the movement information that the user equipment has high mobility.

11. The electronic device according to claim 10, wherein, the movement information includes at least one of the movement speed, movement direction, and residence time of the user equipment.

12. The electronic device according to any one of claims 1 to 11, wherein, the processing circuit is configured to, when it is determined that the user equipment is to non-independently participate in the federated learning, select a user equipment to be cooperatively trained that is to cooperate with the user equipment based on second channel state information of a sidelink between other user equipment within a predetermined range of the user equipment and the user equipment.

13. The electronic device according to claim 12, wherein, the processing circuit is configured to select the following other user equipment as the user equipment to be cooperatively trained: the value of the second channel state information of the sidelink corresponding to the other user equipment is greater than a fourth predetermined threshold.

14. The electronic device according to claim 13, wherein, the second channel state information includes at least one of the signal-to-interference-plus-noise ratio SINR, reference signal received power RSRP, reference signal received quality RSRQ, and reference signal received strength RSRI of the sidelink.

15. The electronic device according to claim 12, wherein, the processing circuit is configured to select other user equipment that satisfies the following conditions as the user equipment to be cooperatively trained based on the second channel state information: via the sidelink corresponding to the other user equipment, the user equipment can transmit model data related to the segmented model corresponding to the user equipment to the other user equipment within a first predetermined time range, and / or the other user equipment can transmit model data related to the segmented model corresponding to the other user equipment to the user equipment within a second predetermined time range.

16. The electronic device according to any one of claims 12 to 15, wherein, the processing circuit is configured to, when the user equipment to be cooperatively trained is selected, determine a segmentation point for segmenting the model to be trained to obtain the segmented model based on the second channel state information.

17. The electronic device according to claim 16, wherein, the processing circuit is configured to make the determined segmentation point satisfy the following conditions: via the sidelink between the user equipment and the user equipment to be cooperatively trained, the user equipment can transmit model data related to the segmented model corresponding to the user equipment to the user equipment to be cooperatively trained within a first predetermined time range, and / or the user equipment to be cooperatively trained can transmit model data related to the segmented model corresponding to the user equipment to be cooperatively trained to the user equipment within a second predetermined time range.

18. The electronic device according to claim 1, wherein, The self-status information includes second channel state information of a sidelink between other user equipment within a predetermined range of the user equipment and the user equipment.

19. The electronic device according to claim 18, wherein the processing circuit is configured to determine that the user equipment is to participate in the federated learning non-independently when there is other user equipment within the predetermined range whose value of the second channel state information is greater than a fifth predetermined threshold.

20. The electronic device according to claim 19, wherein the processing circuit is configured to determine that the user equipment is to participate in the federated learning independently when the second channel state information corresponding to other user equipment within the predetermined range is less than or equal to the fifth predetermined threshold.

21. The electronic device according to claim 19 or 20, wherein, The second channel state information includes at least one of signal-to-interference-plus-noise ratio (SINR), reference signal received power (RSRP), reference signal received quality (RSRQ), and reference signal received intensity (RSRI) of the sidelink.

22. The electronic device according to claim 18, wherein the processing circuit is configured to determine that the user equipment is to participate in the federated learning non-independently when it is determined based on the second channel state information that there is other user equipment satisfying the following conditions: via the sidelink corresponding to the other user equipment, the user equipment can transmit model data related to the segmented model corresponding to the user equipment to the other user equipment within a first predetermined time range, and the other user equipment can transmit model data related to the segmented model corresponding to the other user equipment to the user equipment within a second predetermined time range.

23. The electronic device according to claim 18, wherein the processing circuit is configured to determine that the user equipment is to participate in the federated learning independently when it is determined based on the second channel state information that there is no other user equipment satisfying the following conditions: via the sidelink corresponding to the other user equipment, the user equipment can transmit model data related to the segmented model corresponding to the user equipment to the other user equipment within a first predetermined time range, and the other user equipment can transmit model data related to the segmented model corresponding to the other user equipment to the user equipment within a second predetermined time range.

24. The electronic device according to any one of claims 1 to 23, wherein the processing circuit is configured to send information about the federated learning to the user equipment and the user equipment to be cooperatively trained when it is determined that the user equipment is to participate in the federated learning non-independently and the user equipment to be cooperatively trained for cooperative training with the user equipment is selected.

25. The electronic device according to claim 24, wherein the processing circuit is configured to broadcast the model to be trained and the segmentation points for segmenting the model to be trained to obtain the segmented model to the user equipment and the user equipment to be cooperatively trained.

26. The electronic device according to claim 24, wherein, The processing circuit is configured to send the segmented model corresponding to the user equipment to the user equipment, and send the segmented model corresponding to the user equipment to be coordinated to the user equipment to be coordinated.

27. The electronic device according to any one of claims 24 to 26, wherein, The processing circuit is configured to notify the user equipment and the user equipment to be coordinated to report their trained segmented models respectively, and splice the trained segmented models by the electronic device to obtain the trained complete model.

28. The electronic device according to any one of claims 24 to 26, wherein, The processing circuit is configured to notify the user equipment or the user equipment to be coordinated to splice the trained segmented model to obtain the trained complete model, and report the trained complete model to the electronic device.

29. The electronic device according to any one of claims 24 to 28, wherein, The processing circuit is configured to notify the user equipment and the user equipment to be coordinated of the information about the sidelink between the user equipment and the user equipment to be coordinated.

30. An electronic device for wireless communication, comprising: A processing circuit, configured to: Report the self-state information of the electronic device to the network-side device that provides services for the electronic device, so that the network-side device determines whether the electronic device is to cooperate with other electronic devices to train the segmented model obtained by segmenting the model to be trained in federated learning and thus participate in the federated learning non-independently, or to independently train the model to be trained and thus participate in the federated learning independently.

31. The electronic device according to claim 30, wherein The self-state information includes the first channel state information of the link between the electronic device and the network-side device.

32. The electronic device according to claim 31, wherein The first channel state information includes at least one of the signal-to-interference-plus-noise ratio SINR, reference signal received power RSRP, reference signal received quality RSRQ, and reference signal received intensity RSRI of the uplink between the electronic device and the network-side device.

33. The electronic device according to claim 30, wherein The self-state information includes the computing and storage capacity information of the electronic device.

34. The electronic device according to claim 33, wherein The computing and storage capacity information includes at least one of the CPU occupancy rate and the memory size of the electronic device.

35. The electronic device according to claim 30, wherein The self-state information includes the local data information of the electronic device.

36. The electronic device according to claim 35, wherein The local data information includes the number of training samples and the sample dimension that the electronic device will use when participating in the federated learning independently.

37. The electronic device according to claim 30, wherein The self-state information includes the power information of the electronic device.

38. The electronic device according to claim 30, wherein The self-state information includes the location information of the electronic device.

39. The electronic device according to claim 30, wherein The self-state information includes the movement information of the electronic device.

40. The electronic device according to claim 39, wherein, the movement information includes at least one of the movement speed, movement direction, and stay time of the electronic device.

41. The electronic device according to claim 30, wherein, the self-state information includes second channel state information of a sidelink between other electronic devices within a predetermined range of the electronic device and the electronic device.

42. The electronic device according to any one of claims 30 to 41, wherein, the processing circuit is configured to, when not independently participating in the federated learning, perform the following operations a predetermined number of times on the first segmented model corresponding to the electronic device in each round of global training of the federated learning to obtain a trained first segmented model: transmit first data obtained by training the first segmented model to a cooperating electronic device that cooperates with the electronic device for training, and update the first segmented model based on second data received from the cooperating electronic device, where the second data is obtained by the cooperating electronic device training a second segmented model corresponding to it based on the first data.

43. The electronic device according to claim 42, wherein, the processing circuit is configured to report the trained first segmented model to the network-side device for the network-side device to splice the trained first segmented model and the trained second segmented model received from the cooperating electronic device to obtain a trained complete model, where the trained second segmented model is obtained by the cooperating electronic device training the second segmented model in the global training.

44. The electronic device according to claim 42, wherein, The processing circuit is configured to splice the trained first segmented model and the trained second segmented model to obtain a trained complete model, and report the trained complete model to the network-side device, where the trained second segmented model is obtained by the cooperating electronic device training the second segmented model in the global training.

45. An electronic device for wireless communication, comprising: a processing circuit configured to: report the self-state information of the electronic device to a network-side device that provides services to the electronic device, for the network-side device to determine whether, in the federated learning, the electronic device can cooperate with other electronic devices to train a segmented model obtained by segmenting a model to be trained, so that the other electronic devices non-independently participate in the federated learning, or whether the other electronic devices need to independently train the model to be trained to independently participate in the federated learning.

46. The electronic device according to claim 45, wherein, the self-state information includes third channel state information of a link between the electronic device and the network-side device.

47. The electronic device according to claim 46, wherein, The third channel state information includes at least one of the signal-to-interference-plus-noise ratio (SINR), reference signal received power (RSRP), reference signal received quality (RSRQ), and reference signal received strength (RSRI) of the uplink between the electronic device and the network-side device.

48. The electronic device according to claim 45, wherein, the self-state information includes the computing and storage capacity information of the electronic device.

49. The electronic device according to claim 48, wherein, the computing and storage capacity information includes at least one of the CPU occupancy rate and the memory size of the electronic device.

50. The electronic device according to claim 49, wherein, the self-state information includes the local data information of the electronic device.

51. The electronic device according to claim 50, wherein, the local data information includes the number of training samples and the sample dimension that the electronic device will use when independently participating in the federated learning.

52. The electronic device according to claim 45, wherein, the self-state information includes the power information of the electronic device.

53. The electronic device according to claim 45, wherein, the self-state information includes the location information of the electronic device.

54. The electronic device according to claim 45, wherein, the self-state information includes the movement information of the electronic device.

55. The electronic device according to claim 54, wherein, the movement information includes at least one of the movement speed, movement direction, and stay time of the electronic device.

56. The electronic device according to claim 45, wherein, the self-state information includes other electronic devices within a predetermined range of the electronic device and the fourth channel state information of the sidelink between the electronic device and the other electronic devices.

57. The electronic device according to any one of claims 45 to 56, wherein, the processing circuit is configured to, when the other electronic device does not independently participate in the federated learning, perform the following operations a predetermined number of times on the second segmented model corresponding to the electronic device in each round of global training of the federated learning to obtain a trained second segmented model: receive first data obtained by training the first segmented model corresponding to the other electronic device from the other electronic device, and train the second segmented model based on the first data to obtain second data, and transmit the second data to the other electronic device for the other electronic device to update the first segmented model.

58. The electronic device according to claim 57, wherein, the processing circuit is configured to report the trained second segmented model to the network-side device for the network-side device to splice the trained second segmented model and the trained first segmented model received from the other electronic device to obtain a trained complete model. Among them, the trained first segmented model is obtained by the other electronic device training the first segmented model in the global training.

59. The electronic device according to claim 57, wherein, The processing circuit is configured to splice the trained second segmented model and the trained first segmented model to obtain a trained complete model, and report the trained complete model to the network side device. Among them, the trained first segmented model is obtained by the other electronic device training the first segmented model in the global training.

60. A wireless communication system, comprising: The electronic device according to any one of claims 1 to 29. The electronic device according to any one of claims 30 to 44, and The electronic device according to any one of claims 45 to 59.

61. A method for wireless communication, comprising: Determine, according to the self-status information reported by a user equipment within the service range of an electronic device, whether in federated learning, the user equipment is to cooperate with other user equipment to train a segmented model obtained by segmenting a model to be trained, so as to participate in the federated learning non-independently, or to independently train the model to be trained, so as to participate in the federated learning independently.

62. A method for wireless communication, comprising: Report the self-status information of the electronic device to a network side device that provides services to the electronic device, so that the network side device determines whether in federated learning, the electronic device is to cooperate with other electronic devices to train a segmented model obtained by segmenting a model to be trained, so as to participate in the federated learning non-independently, or to independently train the model to be trained, so as to participate in the federated learning independently.

63. A method for wireless communication, comprising: Report the self-status information of the electronic device to a network side device that provides services to the electronic device, so that the network side device determines whether in federated learning, the electronic device can cooperate with other electronic devices to train a segmented model obtained by segmenting a model to be trained, so that the other electronic devices participate in the federated learning non-independently, or the other electronic devices are to independently train the model to be trained, so as to participate in the federated learning independently.

64. A computer-readable storage medium, on which computer-executable instructions are stored, and when the computer-executable instructions are executed, the method for wireless communication according to any one of solutions 61 to 63 is executed.

Images