A user equipment selection method, device, chip and module device

Abstract

The application discloses a user equipment selection method, device, chip and module equipment. The method comprises the following steps: sending a first message to a first candidate user equipment group; receiving a second message from a second candidate user equipment group; wherein the first candidate user equipment group comprises the second candidate user equipment group; the first message indicates federal learning requirement information, the second message indicates whether the user equipment meets the requirement information, and / or measurement information of the corresponding user equipment; or the first message requests the measurement information, and the second message comprises the measurement information; the requirement information of the federal learning comprises time length requirement information of the federal learning, and / or requirement information of the federal learning on the stability of the user equipment; and the target user equipment group participating in the federal learning is determined based on the second message, and each target user equipment in the target user equipment group meets the requirement information. Through the method, the stability of the user equipment participating in the federal learning can be improved, and the interruption probability of the federal learning can be reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of communication, and in particular to a user equipment selection method, device, chip and module device. BACKGROUND

[0002] Federated learning can obtain an artificial intelligence (AI) model meeting performance requirements of a user on the basis of protecting user data privacy through multi-user joint training, and therefore is concerned in a communication network.

[0003] When selecting participants of federated learning, usually only the computing power information and signal quality of the participants are considered. However, there are cases where the participants cannot completely participate in federated learning, which leads to interruption of federated learning and affects the training delay and accuracy of the trained model of federated learning. How to determine suitable participants to reduce the interruption probability of federated learning is a problem to be solved. SUMMARY

[0004] The present application provides a user equipment selection method, device, chip and module device, which is beneficial to improve the stability of user equipment participating in federated learning and reduce the interruption probability of federated learning.

[0005] In a first aspect, the present application provides a user equipment selection method, which comprises: sending a first message to a first candidate user equipment group; receiving a second message from a second candidate user equipment group, the first candidate user equipment group comprising the second candidate user equipment group; wherein the first message is used to indicate demand information of federated learning, and the second message is used to indicate whether the corresponding user equipment meets the demand information of the federated learning and / or measurement information of the corresponding user equipment; or the first message is used to request measurement information of the user equipment, and the second message comprises the measurement information; the demand information of the federated learning comprises time length demand information of the federated learning and / or demand information of the federated learning on the stability of the user equipment; and based on the second message, a target user equipment group participating in the federated learning is determined, each target user equipment in the target user equipment group meeting the demand information of the federated learning.

[0006] Based on the method described in the first aspect, the network device can select user equipment participating in federated learning according to the time length demand of the federated learning or the demand of the federated learning on the stability of the user equipment, thereby improving the stability of the user equipment participating in the federated learning, trying to ensure that the user equipment can completely participate in the federated learning, and thereby reducing the interruption probability of the federated learning.

[0007] In a possible implementation, the requirement information of the federated learning on the stability of the user equipment includes requirement information on mobility of the user equipment, and / or requirement information on a running state of the user equipment. By implementing the possible implementation, the stability of the mobility or the running state of the user equipment participating in the federated learning can be improved.

[0008] In a possible implementation, the requirement information of the federated learning on the stability of the user equipment includes one or more of the following: mobility level requirement information, location requirement information of the user equipment, computing power change rate requirement information, or signal quality change rate requirement information.

[0009] In a possible implementation, the measurement information includes one or more of the following: a mobility level, a location of the user equipment, a computing power change rate, or a signal quality change rate.

[0010] In a possible implementation, a first indication message is sent to the first candidate user equipment group, the first indication message being used to indicate to update the measurement information.

[0011] In a possible implementation, the first indication message includes the measurement requirement information.

[0012] In a possible implementation, a second indication message is sent to the target user equipment group, the second indication message being used to indicate to continuously monitor whether the requirement information of the federated learning is met; a third indication message is received from a first target user equipment, the third indication message being used to indicate that the first target user equipment does not meet the requirement information of the federated learning, the first target user equipment being one of the target user equipment group; the first target user equipment is removed from the target user equipment group; or, a priority of the first target user equipment in the target user equipment group is reduced.

[0013] In a possible implementation, the second indication message further includes the requirement information of the federated learning.

[0014] In a possible implementation, a fourth indication message is received from another network device, the fourth indication message being used to indicate the measurement information of at least one user equipment, the fourth indication message being used to determine the first candidate user equipment group.

[0015] In a possible implementation, a fifth indication message is sent to another network device, the fifth indication message being used to indicate the measurement information of at least one user equipment.

[0016] In a possible implementation, when performing handover for a second target user equipment, the second target user equipment being one of the target user equipment group, the second target user equipment is released; and the second target user equipment is removed from the target user equipment group.

[0017] In a possible implementation, a secondary node addition request message is sent to the neighboring base station, the secondary node addition request message being used to establish a communication connection between the third target user equipment and the neighboring base station; the third target user equipment is one of the target user equipment group. By implementing the possible implementation, when the user equipment participating in the federated learning is at the cell edge, the network device can establish a dual connection for the user equipment to ensure that the user equipment can complete the participation in the federated learning, thereby reducing the interruption probability of the federated learning.

[0018] In a possible implementation, a sixth indication message is sent to the neighboring base station, the sixth indication message being used to indicate that the federated learning data of the third target user equipment is sent; and the federated learning data of the third target user equipment is received from the neighboring base station.

[0019] In a second aspect, the present application provides a user equipment selection method, the method comprising: receiving a first message from a network device; and sending a second message to the network device; wherein the first message is used to indicate demand information of federated learning, and the second message is used to indicate whether the corresponding user equipment meets the demand information of the federated learning and / or measurement information of the corresponding user equipment; or the first message is used to request measurement information of the user equipment, and the second message comprises the measurement information; the demand information of the federated learning comprises time length demand information of the federated learning and / or demand information of user equipment stability of the federated learning.

[0020] The method described in the first aspect has the beneficial effects described in the foregoing first aspect, and the repeated parts will not be described in detail here.

[0021] In a possible implementation, the demand information of user equipment stability of the federated learning comprises demand information of user equipment mobility and / or demand information of user equipment running state.

[0022] In a possible implementation, the demand information of user equipment stability of the federated learning comprises one or more of the following: mobility level demand information, location demand information of the user equipment, computing power change rate demand information, or signal quality change rate demand information.

[0023] In a possible implementation, the measurement information comprises one or more of the following: mobility level, location of the user equipment, computing power change rate, or signal quality change rate.

[0024] In a possible implementation, a first indication message is received from the network device, the first indication message being used to indicate that the measurement information is updated; and the measurement information is updated based on the first indication message.

[0025] In a possible implementation, the first indication message comprises measurement requirement information, and the measurement information is updated based on the first indication message if the user equipment does not satisfy the measurement requirement information.

[0026] In a possible implementation, a second indication message is received from the network equipment, the second indication message being used to indicate whether the requirement information of the federated learning is satisfied by the continuous monitoring; and a third indication message is sent to the network equipment, the third indication message being used to indicate that the requirement information of the federated learning is not satisfied by the user equipment.

[0027] In a possible implementation, the second indication message further comprises the requirement information of the federated learning.

[0028] In a third aspect, the present application provides a user equipment selection apparatus, comprising: a sending unit configured to send a first message to a first candidate user equipment group; a receiving unit configured to receive a second message from a second candidate user equipment group, the first candidate user equipment group comprising the second candidate user equipment group; wherein the first message is used to indicate requirement information of a federated learning, the second message is used to indicate whether the requirement information of the federated learning is satisfied by a corresponding user equipment and / or measurement information of the corresponding user equipment; or the first message is used to request the measurement information of the user equipment, and the second message comprises the measurement information; the requirement information of the federated learning comprises time length requirement information of the federated learning and / or requirement information of the federated learning on stability of the user equipment; and a determining unit configured to determine a target user equipment group participating in the federated learning based on the second message, each target user equipment in the target user equipment group satisfying the requirement information of the federated learning.

[0029] In a possible implementation, the requirement information of the federated learning on stability of the user equipment comprises requirement information on mobility of the user equipment and / or requirement information on running state of the user equipment.

[0030] In a possible implementation, the requirement information of the federated learning on stability of the user equipment comprises one or more of the following: mobility level requirement information, location requirement information of the user equipment, change rate requirement information of computing power or change rate requirement information of signal quality.

[0031] In a possible implementation, the measurement information comprises one or more of the following: mobility level, location of the user equipment, change rate of computing power or change rate of signal quality.

[0032] In a possible implementation, the sending unit is further configured to send a first indication message to the first candidate user equipment group, the first indication message being used to indicate that the measurement information is updated.

[0033] In a possible implementation, the first indication message comprises measurement requirement information.

[0034] In a possible implementation, the sending unit is further configured to send a second indication message to the target user equipment group, the second indication message being used to indicate whether the continuous monitoring meets the requirement information of federated learning; the receiving unit is further configured to receive a third indication message of a first target user equipment, the third indication message being used to indicate that the first target user equipment does not meet the requirement information of federated learning, the first target user equipment being one of the target user equipment group; the determining unit is further configured to remove the first target user equipment from the target user equipment group; or, reduce the priority of the first target user equipment in the target user equipment group.

[0035] In a possible implementation, the second indication message further comprises the requirement information of federated learning.

[0036] In a possible implementation, the receiving unit is further configured to receive a fourth indication message from another network device, the fourth indication message being used to indicate the measurement information of at least one user equipment, the fourth indication message being used to determine the first candidate user equipment group.

[0037] In a possible implementation, the sending unit is further configured to send a fifth indication message to another network device, the fifth indication message being used to indicate the measurement information of at least one user equipment.

[0038] In a possible implementation, when performing handover for a second target user equipment, the determining unit is further configured to release the second target user equipment, the second target user equipment being one of the target user equipment group; and remove the second target user equipment from the target user equipment group.

[0039] In a possible implementation, the sending unit is configured to send a secondary node addition request message to a neighboring base station, the secondary node addition request message being used to establish a communication connection between the third target user equipment and the neighboring base station; the third target user equipment being one of the target user equipment group.

[0040] In a possible implementation, the sending unit is configured to send a sixth indication message to a neighboring base station, the sixth indication message being used to indicate that the federated learning data of the third target user equipment is sent; and receive the federated learning data of the third target user equipment from the neighboring base station.

[0041] In a fourth aspect, the present application provides a user equipment selection apparatus, comprising: a receiving unit configured to receive a first message from a network device; and a sending unit configured to send a second message to the network device, wherein the first message is configured to indicate federated learning requirement information, and the second message is configured to indicate whether a corresponding user equipment satisfies the federated learning requirement information and / or measurement information of the corresponding user equipment; or the first message is configured to request measurement information of the user equipment, and the second message comprises the measurement information; and the federated learning requirement information comprises federated learning duration requirement information and / or federated learning requirement information on user equipment stability.

[0042] The method described in the first aspect has the beneficial effects described above in relation to the first aspect, and the repeated beneficial effects will not be described again in detail.

[0043] In a possible implementation, the federated learning requirement information on user equipment stability comprises requirement information on user equipment mobility and / or requirement information on user equipment running state.

[0044] In a possible implementation, the federated learning requirement information on user equipment stability comprises one or more of the following: mobility level requirement information, location requirement information of the user equipment, computing power change rate requirement information, or signal quality change rate requirement information.

[0045] In a possible implementation, the measurement information comprises one or more of the following: mobility level, location of the user equipment, computing power change rate, or signal quality change rate.

[0046] In a possible implementation, the receiving unit is further configured to receive a first indication message from the network device, the first indication message being configured to indicate to update the measurement information; and the measurement information is updated based on the first indication message.

[0047] In a possible implementation, the apparatus further comprises an updating unit, the first indication message comprises measurement requirement information, and the updating unit is configured to update the measurement information based on the first indication message if the user equipment does not satisfy the measurement requirement information.

[0048] In a possible implementation, the receiving unit is further configured to receive a second indication message from the network device, the second indication message being configured to indicate whether to continue monitoring the federated learning requirement information; and the sending unit is further configured to send a third indication message to the network device, the third indication message being configured to indicate that the user equipment does not satisfy the federated learning requirement information.

[0049] In a possible implementation, the second indication message further comprises the federated learning requirement information.

[0050] In a fifth aspect, the present application provides a chip comprising a processor and a communication interface, the processor being configured to perform the following operations: sending a first message to a first candidate user equipment group; receiving a second message from a second candidate user equipment group, the first candidate user equipment group comprising the second candidate user equipment group; wherein the first message is used to indicate requirement information of federated learning, the second message is used to indicate whether the corresponding user equipment satisfies the requirement information of federated learning and / or measurement information of the corresponding user equipment; or the first message is used to request measurement information of the user equipment, and the second message comprises the measurement information; the requirement information of federated learning comprises time length requirement information of federated learning and / or requirement information of user equipment stability of federated learning; based on the second message, determining a target user equipment group participating in federated learning, each target user equipment in the target user equipment group satisfying the requirement information of federated learning.

[0051] In a sixth aspect, the present application provides a chip comprising a processor and a communication interface, the processor being configured to perform the following operations: receiving a first message from a network device; sending a second message to the network device; wherein the first message is used to indicate requirement information of federated learning, and the second message is used to indicate whether the corresponding user equipment satisfies the requirement information of federated learning and / or measurement information of the corresponding user equipment; or the first message is used to request measurement information of the user equipment, and the second message comprises the measurement information; the requirement information of federated learning comprises time length requirement information of federated learning and / or requirement information of user equipment stability of federated learning.

[0052] In a seventh aspect, the present application provides a module device comprising a communication module, a power supply module, a storage module and a chip, wherein: the power supply module is used to provide electric energy for the module device; the storage module is used to store data and instructions; the communication module is used for internal communication of the module device or for communication between the module device and an external device; and the chip is used to: send a first message to a first candidate user equipment group; receive a second message from a second candidate user equipment group, the first candidate user equipment group comprising the second candidate user equipment group; wherein the first message is used to indicate requirement information of federated learning, and the second message is used to indicate whether the corresponding user equipment satisfies the requirement information of federated learning and / or measurement information of the corresponding user equipment; or the first message is used to request measurement information of the user equipment, and the second message comprises the measurement information; the requirement information of federated learning comprises time length requirement information of federated learning and / or requirement information of user equipment stability of federated learning; based on the second message, determine a target user equipment group participating in federated learning, each target user equipment in the target user equipment group satisfying the requirement information of federated learning.

[0053] In an eighth aspect, the present application provides a module device, comprising a communication module, a power supply module, a storage module, and a chip, wherein: the power supply module is configured to provide power for the module device; the storage module is configured to store data and instructions; the communication module is configured to perform internal communication of the module device, or to perform communication between the module device and an external device; and the chip is configured to: receive a first message from a network device; and send a second message to the network device; wherein the first message is configured to indicate demand information of federated learning, the second message is configured to indicate whether a corresponding user device meets the demand information of federated learning, and / or measurement information of the corresponding user device; or the first message is configured to request measurement information of the user device, and the second message comprises the measurement information; and the demand information of federated learning comprises time length demand information of federated learning, and / or demand information of user device stability of federated learning.

[0054] In a ninth aspect, the embodiments of the present application disclose a network device, comprising a memory and a processor, the memory is configured to store a computer program, the computer program comprises program instructions, and the processor is configured to invoke the program instructions to execute the method in the first aspect and any possible implementation manner thereof.

[0055] In a tenth aspect, the embodiments of the present application disclose a user device, comprising a memory and a processor, the memory is configured to store a computer program, the computer program comprises program instructions, and the processor is configured to invoke the program instructions to execute the method in the second aspect and any possible implementation manner thereof.

[0056] In an eleventh aspect, the present application provides a computer readable storage medium, the computer readable storage medium stores computer readable instructions, when the computer readable instructions run on a communication device, the communication device executes the method in the first aspect and any possible implementation manner thereof, or executes the method in the second aspect and any possible implementation manner thereof.

[0057] In a twelfth aspect, the present application provides a computer program or a computer program product, comprising code or instructions, when the code or instructions run on a computer, the computer executes the method in the first aspect and any possible implementation manner thereof, or executes the method in the second aspect and any possible implementation manner thereof. BRIEF DESCRIPTION OF DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort.

[0059] Figure 1 This is a schematic diagram of a communication system provided in an embodiment of this application;

[0060] Figure 2 This is a schematic diagram of a federated learning process provided in an embodiment of this application;

[0061] Figure 3 This is a flowchart illustrating a user equipment selection method provided in an embodiment of this application;

[0062] Figure 4 This is a flowchart illustrating a user equipment selection method provided in an embodiment of this application;

[0063] Figure 5 This is a flowchart illustrating a user equipment selection method provided in an embodiment of this application;

[0064] Figure 6 This is a flowchart illustrating an optimization scheme for user equipment selection provided in an embodiment of this application;

[0065] Figure 7a This is a flowchart illustrating an optimization scheme for user equipment selection provided in an embodiment of this application;

[0066] Figure 7b This is a flowchart illustrating an optimization scheme for user equipment selection provided in an embodiment of this application;

[0067] Figure 8 This is a flowchart illustrating an optimization scheme for user equipment selection provided in an embodiment of this application;

[0068] Figure 9 This is a schematic diagram of the structure of a user equipment selection device provided in an embodiment of this application;

[0069] Figure 10 This is a schematic diagram of another user equipment selection device provided in an embodiment of this application;

[0070] Figure 11 This is a schematic diagram of the structure of a network device provided in an embodiment of this application;

[0071] Figure 12 This is a schematic diagram of the structure of a user equipment provided in an embodiment of this application;

[0072] Figure 13 This is a schematic diagram of the structure of a module device provided in an embodiment of this application. Detailed Implementation

[0073] The specific embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0074] The terms "first" and "second" and the like in the description and in the claims of this application are used for distinguishing between similar elements and not necessarily for describing a specific sequential or chronological order. Descriptions using the terms "including", "containing" or "comprising" and variations thereof do not specify an exhaustive or closed set of elements or steps, but rather add or remove equivalents of the specifically recited elements or steps based on the context and / or as further specific inclusion, exclusion and / or preferences are given in the description, the claims and / or the figures. Nothing in the above description shall limit the application except as recited in the claims.

[0075] Reference herein to "an embodiment" or "one embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. The appearances of the phrase "in one embodiment" or "in an embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily referring to a common or identical embodiment. It is expressly understood that the embodiments described herein are merely examples from a great number of possible embodiments.

[0076] In this application, "at least one", "one or more", "multiple", "two or more", "at least two", "and / or", are used to describe a combination which can include only one, or only a plurality of the associated items. For example, "A and / or B" means only A, only B, or A and B. The character " / " is generally used to indicate "or" relationship between the associated objects. "At least one of the following" or similar expressions means any combination of these items, including single item or combination of multiple items. For example, at least one of a, b or c, means a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0077] In order to better understand the embodiments of the present application, first, the communication system related to the embodiments of the present application is introduced as follows:

[0078] The technical solutions of the embodiments of the present application can be applied to various communication systems, for example: a global system of mobile communication (GSM) system, a code division multiple access (CDMA) system, a wideband code division multiple access (WCDMA) system, a general packet radio service (GPRS), a long term evolution (LTE) system, an LTE frequency division duplex (FDD) system, an LTE time division duplex (TDD), a universal mobile telecommunication system (UMTS), a worldwide interoperability for microwave access (WiMAX) communication system, a 5th generation (5G) system or a new radio (NR), and a future communication system, etc.

[0079] Figure 1 is a schematic diagram of a communication system provided by an embodiment of the present application. The scheme in the present application can be applied to the communication system, which can include a network device and a user equipment. It should be noted that, Figure 1 is an example of including 1 network device and 2 user equipments in the communication system, which should not be regarded as a specific limitation of the present application.

[0080] I. User equipment (UE)

[0081] The user equipment includes a device providing voice and / or data connectivity to a user, e.g., a user equipment is a device having wireless transceiver function, which can be deployed on land, including indoor or outdoor, handheld, wearable or vehicle-mounted; can also be deployed on water surface (such as ships, etc.); can also be deployed in the air (such as airplanes, balloons and satellites, etc.). The terminal can be a mobile phone, a vehicle, a roadside unit, a tablet computer (Pad), a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal in industrial control, a vehicle-mounted terminal device, a wireless terminal in self driving, a wireless terminal in remote medical, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, a wearable terminal device, etc. The embodiments of the present application do not limit the application scenarios. The terminal can also be referred to as a terminal device, an access terminal device, a vehicle-mounted terminal, an industrial control terminal, a UE unit, a UE station, a mobile station, a mobile station, a remote station, a remote terminal device, a mobile device, a UE terminal device, a terminal device, a wireless communication device, a UE agent or a UE apparatus, etc. The terminal can also be fixed or mobile. In the embodiments of the present application, the device for realizing the function of the terminal device can be the terminal device, or can be a device capable of supporting the terminal device to realize the function, such as a chip system or a combination device, component capable of realizing the function of the terminal device, which can be installed in the terminal device.

[0082] II. Network device

[0083] The network device is a node or device for connecting the terminal device to the wireless network. The network device mentioned in the present application can include, but is not limited to, a base station, an evolved NodeB (eNodeB), a transmission reception point (TRP), a next generation NodeB (gNB) in a 5th generation (5G) mobile communication system, a next generation NodeB in a 6th generation (6G) mobile communication system, a base station in a future mobile communication system, or an access node in a WiFi system, etc. The base station mentioned in the present application can also be a module or unit that completes the function of the base station, for example, it can be a central unit (CU) or a distributed unit (DU). The CU completes the function of the radio resource control protocol and the packet data convergence protocol (PDCP) of the base station, and can also complete the function of the service data adaptation protocol (SDAP); the DU completes the function of the radio link control layer and the medium access control (MAC) layer of the base station, and can also complete the function of part of the physical layer or the entire physical layer. For specific description of each protocol layer, reference can be made to the relevant technical specifications of the 3rd generation partnership project (3GPP). The network device can be a macro base station, a micro base station or an indoor station, and can also be a relay node or a donor node, etc.

[0084] The network device mentioned in the present application can also be one or more CN devices in a core network (CN). For example, the network device mentioned in the present application can be one or more of the following CN devices: a network slice selection function (NSSF), a network exposure function (NEF), a network function repository function (NRF), a policy control function (PCF), a unified data management (UDM), an application function (AF), a network control function (NCF), a network slice specific authentication and authorization function (NSSAAF), an authentication server function (AUSF), an access and mobility management function (AMF), a session management function (SMF), a user plane function (UPF), a service communication proxy (SCP), a network slice admission control (NSACF).

[0085] In the embodiments of the present application, the device for implementing the function of the network device can be the network device itself, or a device capable of supporting the network device to implement the function, such as a chip system or a combined device or component capable of implementing the function of the access network device, which can be installed in the network device. The embodiments of the present application do not limit the specific technology and specific device form adopted by the network device.

[0086] In order to facilitate understanding of the technical solutions of the present application, the federated learning will be explained and described first.

[0087] The federal learning is mainly a solution to the data island problem. The goal of federal learning is to realize joint modeling of multiple participants to improve the effect of AI model on the basis of ensuring data privacy and safety and legality. The federal learning can be understood as a distributed machine learning technology. The process of federal learning can be divided into one round of federal learning and multiple rounds of federal learning. The one round of federal learning process is exemplarily illustrated below, please refer to Figure 2 Figure 2 FIG. 1 is a flowchart of a federal learning process.

[0088] In S201, the server corresponding to the federal learning sends a resource request to multiple candidate user devices.

[0089] In S202, the server corresponding to the federal learning receives resource information reported by each candidate user device.

[0090] In S203, the server corresponding to the federal learning determines user devices participating in the federal learning according to the resource information sent by each candidate user device.

[0091] In S204, the server corresponding to the federal learning distributes a global model to each user device participating in the federal learning.

[0092] In S205, each user device participating in the federal learning updates the global model to obtain updated model parameters (including model weights and gradient values).

[0093] In S206, the server corresponding to the federal learning receives the updated model parameters sent by each user device participating in the federal learning.

[0094] In addition, the server corresponding to the federal learning can also send an acknowledge character (ACK) signal to each user device participating in the federal learning after receiving the updated model parameters sent by each user device participating in the federal learning.

[0095] In S207, the server corresponding to the federal learning aggregates the model according to each updated model parameter.

[0096] Generally, when selecting user devices participating in the federal learning (or referred to as participants), the participating user devices are determined based on computing power information and signal quality. However, the stability of the user devices determined in this way in the process of participating in the federal learning cannot be guaranteed, that is, there may be a case that the participating user devices cannot completely participate in the federal learning, which leads to interruption of the federal learning and affects the training time delay and the accuracy of the trained model of the federal learning.

[0097] ​To improve the reliability and stability of user equipment participating in federated learning, the present application provides a user equipment selection method, device, chip and module device. The user equipment selection method, device, chip and module device provided by the embodiments of the present application are further described in detail below.

[0098] Figure 3 is a flowchart of a user equipment selection method provided by an embodiment of the present application. As shown in Figure 3 , the user equipment selection method comprises the following S301-S303. Figure 3 The method execution subject shown in Figure 3 may be a user equipment or a chip in the user equipment. Alternatively, Figure 3 The method execution subject shown in may be a network device or a chip in the network device.

[0099] Take the user equipment and the network device as the method execution subject for example.

[0100] In other words, the network device selects a first candidate user equipment group and sends a first message to each candidate user equipment in the first candidate user equipment group.

[0101] For ease of understanding, the first message will be described first, and then the process of the network device selecting the first candidate user equipment group will be described.

[0102] The content indicated by the first message can be divided into the following two cases, please refer to Figure 4 and Figure 5 , Figure 4 and Figure 5 are flowcharts of the user equipment selection method provided by the present application, wherein:

[0103] Case one: please refer to S401 shown in Figure 4 , the network device sends a first message to a plurality of candidate user equipments (i.e. a first candidate user equipment group), and the first message is used to indicate the demand information of federated learning.

[0104] Among them, the demand information of federated learning includes the time length demand information of federated learning, and / or the demand information of user equipment stability of federated learning. It should be understood that the time length demand information of federated learning is used to indicate the time length of the user equipment occupied by the federated learning. The demand information of user equipment stability of federated learning is used to indicate the device stability condition of the user equipment participating in the federated learning.

[0105] In a possible implementation, the requirement information of the federated learning on the stability of the user equipment includes requirement information of mobility of the user equipment, and / or requirement information of a running state of the user equipment. The requirement information of the mobility of the user equipment can be understood as that the user equipment is of a low mobility level, the user equipment is not at a cell edge, or a signal quality change rate of the user equipment is not greater than a first threshold, and the like. The requirement information of the running state of the user equipment can be understood as that a computing power change rate of the user equipment is not greater than a second threshold, and the like. The specific value of the first threshold and the specific value of the second threshold can be adjusted according to a specific application scenario, which is not limited in the present application.

[0106] In another possible implementation, the requirement information of the federated learning on the stability of the user equipment includes, but is not limited to, one or more of the following information: mobility level requirement information, location requirement information of the user equipment, computing power change rate requirement information, or signal quality change rate requirement information.

[0107] It should be stated that, in addition to the above-mentioned requirement information (i.e., the time length requirement information of the federated learning and the requirement information of the federated learning on the stability of the user equipment), the requirement information of the federated learning mentioned in the present application can also include other requirement information, such as requirement information of the federated learning on computing power, requirement information of the federated learning on signal quality, and the like.

[0108] Case two: please refer to Figure 5 As shown in S501 in the above-mentioned method, the network device sends a first message to a plurality of candidate user equipment (i.e., a first candidate user equipment group), and the first message is used to request measurement information of the user equipment.

[0109] In other words, the user equipment receiving the first message can report the measurement information of the user equipment. The measurement information includes internal measurement information (such as a computing power change rate, a temperature change rate, and the like) of the user equipment, and air interface measurement information (such as a mobility level, a signal quality change rate, and the like).

[0110] In a possible implementation, the measurement information includes, but is not limited to, one or more of the following information: a mobility level, a location of the user equipment, a change rate of computing power, or a change rate of signal quality. It needs to be understood that the mobility level is used to indicate the mobility of the user equipment, for example, the mobility level of the user equipment is low mobility (that is, it can be understood that the user equipment does not move, does not move frequently, or only moves within an authorized area); the location information of the user equipment is used to indicate the relative location information of the user equipment in the cell where it is located, and the user equipment can perceive the relative location information in the cell where it is located according to signal quality and other information; the change rate of computing power is used to indicate the change amount of computing power of the user equipment in a period of time (for example, 1 hour), and the smaller the change rate of computing power, the more stable the user equipment; the change rate of signal quality is used to indicate the change amount of signal quality of the user equipment in a period of time (for example, 1 hour), and the smaller the change rate of signal quality, the more stable the user equipment.

[0111] After the first message is described, the process of selecting the first candidate user equipment group by the network device is described below.

[0112] The process of selecting the first candidate user equipment group by the network device can be understood as that the network device obtains a plurality of user equipment information recorded on the network side, and selects a plurality of user equipments that can participate in federated learning (that is, candidate user equipments) according to the plurality of user equipment information, and these user equipments that can participate in federated learning constitute the first candidate user equipment group.

[0113] It needs to be noted that the network side described above can be the network device itself, or other devices (which can be understood as devices that have a communication connection with the network device). The user equipment information includes, but is not limited to, capability information or computing power information. The capability information is used to describe the capability of the user equipment, including but not limited to the capability of supporting federated learning; the computing power information is used to describe the computing performance of the user equipment, which can describe the number of operations that can be performed by the user equipment per second (or in a period of time). In other words, in a possible implementation, the network device receives a fourth indication message from other network devices, and the fourth indication message is used to indicate the measurement information of at least one user equipment, and the fourth indication message is used to determine the first candidate user equipment group. Similarly, in another possible implementation, the network device can also send a fifth indication message to other network devices, and the fifth indication message is used to indicate the measurement information of at least one user equipment, and the measurement information of the at least one user equipment is used by other network devices to determine the candidate user equipment of other federated learning (or the next round of federated learning of the federated learning).

[0114] For example, the network device obtains the information of a plurality of user equipments recorded on the network side, which can be seen from Table 1.

[0115] Table 1

[0116] User equipment identity Capability information Computing power information UE1 Supports federated learning 4.1 x 10 9 ]]> UE2 Supports federated learning 6 x 10 9 ]] UE3 Supports federated learning 5.3 x 10 9 ]] UE4 Supports federated learning 4.8 x 10 9 ]] UE5 Supports federated learning 4.5 x 10 9 ]]> UE6 Supports federated learning 3.2 x 10 9 ]]> UE7 Does not support federated learning 6.2 x 10 9 ]]>

[0117] The network device selects a plurality of user devices (i.e., a first candidate user device group) that are likely to participate in the federated learning according to the information of the plurality of user devices recorded by the network side shown in Table 1 and the requirement information of the federated learning (for example, the requirement information of the federated learning for computing power is 3.5 x 10 9 The network device sends the requirement information of the federated learning to the plurality of user devices (i.e., UE1, UE2, UE3, UE4, and UE5) that are likely to participate in the federated learning. The network device can send the requirement information of the federated learning in a one-to-one unicast manner or in a one-to-many multicast manner, which is not limited in the present application.

[0118] S302, the network device receives a second message from a second candidate user device group, and the first candidate user device group includes the second candidate user device group.

[0119] In other words, the user devices in the first candidate user device group can choose to send the second message to the network device after receiving the first message, or can not send the second message to the network device. It can be understood that the number of user devices in the second candidate user device group is less than or equal to the number of user devices in the first candidate user device group, and the second candidate user device group is a subset of the first candidate user device group. It should be noted that if the network device does not receive the second message sent by a candidate user device within a certain time period, the candidate user device is considered to refuse to participate in the federated learning.

[0120] The second message will be described below in combination with two cases of the first message in S301.

[0121] Case one: the first message is used to indicate the requirement information of the federated learning. In this case, the second message is used to indicate whether the corresponding user device meets the requirement information of the federated learning and / or the measurement information of the corresponding user device.

[0122] In other words, in this case, after receiving the first message from the network device, each candidate user device evaluates whether to participate in the federated learning based on the measurement information of the candidate user device and the requirement information of the federated learning, as shown in S402 in Figure 4 Figure 4 ​When the measurement information of the candidate user equipment satisfies the requirement information of the federated learning, the candidate user equipment can send a second message to the network equipment, where the second message is used to indicate that the requirement information of the federated learning is satisfied (i.e., the federated learning is accepted) and / or the measurement information of the candidate user equipment.

[0123] In one possible implementation, when the measurement information of the candidate user equipment does not satisfy the requirement information of the federated learning, the candidate user equipment can not send the second message to the network equipment. Alternatively, the candidate user equipment can also send the second message to the network equipment, where the second message is used to indicate that the requirement information of the federated learning is not satisfied (i.e., the federated learning is rejected) and / or the measurement information of the candidate user equipment.

[0124] Case two: the first message is used to request the measurement information of the user equipment. In this case, the candidate user equipment sends a second message to the network equipment, where the second message includes the measurement information of the corresponding user equipment.

[0125] In other words, in this case, the candidate user equipment receives the first message from the network equipment, and then the candidate user equipment sends the second message to the network equipment, where the second message includes the measurement information of the corresponding user equipment. Figure 5 As shown in S502, each candidate user equipment sends a second message to the network equipment, where the second message is used to indicate the measurement information of the candidate user equipment itself, so that after the network equipment receives the second message, the network equipment can evaluate whether the candidate user equipment can participate in the federated learning according to the second message.

[0126] It can be seen that the measurement information of the candidate user equipment is the key to evaluate whether the candidate user equipment satisfies the requirement information of the federated learning. The following describes the way in which the candidate user equipment obtains the measurement information of itself. It should be noted that the following way (i.e., the following way one or way two) in which the candidate user equipment obtains the measurement information of itself is applicable to the aforementioned case one and case two.

[0127] Way one: after the candidate user equipment receives the first message, the candidate user equipment obtains the recorded measurement information of the user equipment from the storage space.

[0128] For example, at a first time, the candidate user equipment A performs measurement and obtains the measurement information as follows: low mobility, not at the cell edge, the change rate of computing power is 0.1, and the change rate of signal quality is 0.2. Further, the candidate user equipment A records and stores the measurement information at the first time. In this case, if the candidate user equipment A receives the requirement information of the federated learning at a second time (a certain time after the first time), the candidate user equipment A obtains the measurement information at the first time from the storage space, and can quickly evaluate whether the requirement information of the federated learning is satisfied according to the measurement information, thereby improving the evaluation efficiency.

[0129] But since the measurement information recorded in the storage space of the user equipment has timeliness, it can be understood that the mobility level of the user equipment, the location information of the user equipment, the change rate of the computing power or the change rate of the signal quality can change over time. In other words, the smaller the time interval between the first time and the second time, the closer the measurement information at the first time is to the real measurement information corresponding to the user equipment at the second time. If the time interval between the first time and the second time is large, it may lead to evaluation failure.

[0130] In order to avoid the situation of evaluation failure due to the timeliness of the measurement information, in one possible implementation, before receiving the second message, the network device sends a first indication message to the candidate user equipment, the first indication message being used to indicate updating the measurement information.

[0131] In other words, the candidate user equipment receives the first indication message from the network device, the first indication message being used to indicate updating the measurement information, and further, the candidate user equipment updates the measurement information according to the first indication message. By updating the measurement information in this way, the accuracy of the measurement information is ensured.

[0132] In another possible implementation, before receiving the second message, the network device sends a first indication message to the candidate user equipment, the first indication message being used to indicate updating the measurement information, and the first indication message further including measurement requirement information. The measurement requirement information includes but is not limited to the time requirement of the measurement information (for example, the measurement information within 5 minutes from the time when the user equipment receives the first message).

[0133] In other words, the candidate user equipment receives the first indication message from the network device, the first indication message being used to indicate updating the measurement information, and the first indication message further including the measurement requirement information. If the candidate user equipment does not meet the measurement requirement information, the measurement information is updated based on the first indication message.

[0134] For example, the measurement requirement information is "the measurement information within 5 minutes from the time when the first message is received", and if the measurement information stored in the storage space of the candidate user equipment A is recorded at the first time, the candidate user equipment A receives the requirement information of federated learning at the second time (a certain time after the first time), and the interval between the first time and the second time is 10 minutes, it can be considered that the candidate user equipment A does not meet the measurement requirement information. Further, the candidate user equipment A updates the measurement information based on the first indication message.

[0135] It should be noted that updating the measurement information based on the first indication message can be understood as follows: if the first indication message includes measurement configuration parameters, the candidate user equipment updates the measurement information according to the measurement configuration parameters in the first indication message; if the first indication message does not include measurement configuration parameters, the candidate user equipment updates the measurement information according to preconfigured measurement configuration parameters. The measurement configuration parameters include but are not limited to one or more of the following: measurement target, data format, measurement duration, or measurement frequency.

[0136] Option 2: After the candidate user equipment receives the first message, the candidate user equipment performs real-time measurement on the user equipment according to the requirement information of the federated learning, and obtains the measurement information of the candidate user equipment.

[0137] In this way, the candidate user equipment can perform real-time measurement according to the specific content of the requirement information of the federated learning, and obtain the measurement information of the candidate user equipment.

[0138] For example, the requirement information of the federated learning includes requirement information of user equipment mobility and requirement information of user equipment running state. The candidate user equipment measures the mobility related information (such as mobility level, signal quality change rate or user equipment position) of the user equipment and measures the running state related information (such as computing power change rate) of the user equipment according to the requirement information of the federated learning, and obtains the measurement information.

[0139] S303, the network device determines a target user equipment group participating in the federated learning based on the second message, and each target user equipment in the target user equipment group meets the requirement information of the federated learning.

[0140] After the network device receives the response message of each candidate user equipment in the second candidate user equipment group, the network device determines a plurality of target user equipments from the candidate user equipments whose measurement information meets the requirement information of the federated learning, and the plurality of target user equipments are used to participate in the federated learning, that is, the plurality of target user equipments are the target user equipment group participating in the federated learning. Further, the network device establishes a protocol data unit (PDU) session between each target user equipment, and the network device sends configuration parameters of participating in the federated learning to each target user equipment in the plurality of target user equipments, and each target user equipment starts federated learning according to the configuration parameters.

[0141] For example, the network device receives the response messages from the UEs 1-5, wherein the response messages sent by the UEs 1-4 are the response messages participating in the federated learning, and the response message sent by the UE 5 is the response message refusing the federated learning. In this case, the network device can determine the UEs 1-4 as the target user equipment participating in the federated learning; or the network device can select part of the user equipment from the UEs 1-4 as the target user equipment participating in the federated learning.

[0142] In one possible implementation, when the second message is used to indicate whether the corresponding user equipment meets the requirement information of the federated learning, and / or the measurement information of the corresponding user equipment, please refer to S404 shown in Figure 4 , the network device determines the target user equipment group participating in the federated learning based on the second message. It can be understood that the network device determines the target user equipment group from the candidate user equipment indicated by the second message to meet the requirement information of the federated learning. In other words, whether to participate in the federated learning is evaluated (or decided) by the user equipment.

[0143] In another possible implementation, when the second message includes the measurement information of the corresponding user equipment, please refer to S503 shown in Figure 5 , the network device determines the target user equipment group participating in the federated learning based on the second message. It can be understood that the network device evaluates whether the measurement information of each candidate user equipment meets the requirement information of the federated learning according to the measurement information of each candidate user equipment, and determines multiple target user equipment from the candidate user equipment whose measurement information meets the requirement information of the federated learning. In other words, whether to participate in the federated learning is evaluated (or decided) by the network device.

[0144] It can be seen that, based on the user equipment selection method provided in Figure 3 , the stability of the user equipment participating in the federated learning can be improved, and it is ensured that the user equipment can participate in the federated learning completely, thereby reducing the interruption probability of the federated learning.

[0145] In order to enhance the stability of the participating user equipment and the robustness of the federated learning, based on any of the provided methods, after the network device determines the target user equipment group, the present application further provides the following optimization schemes, please refer to Figures 3-5 , Figure 6 , Figure 7a , Figure 7b or Figure 8 .

[0146] Please refer to Figure 6 , Figure 6 is a flowchart of an optimization scheme of a user equipment selection provided by the present application, which is achieved by Figure 6The method shown can continuously monitor each target user equipment, so that the network device knows the running state of each target user equipment.

[0147] S601, the network device sends a second indication message to each target user equipment in the target user equipment group, the second indication message being used to indicate whether the continuous monitoring meets the requirement information of the federated learning.

[0148] In other words, after the network device selects the multiple target user equipments participating in the federated learning, the network device sends an indication message to each target user equipment, indicating whether the continuous monitoring of the measurement information of each target user equipment meets the requirement information of the federated learning in the process of the federated learning. In a possible implementation, in the case that the target user equipment does not perceive (or understand) the requirement information of the federated learning, the second indication message further includes the requirement information of the federated learning.

[0149] It should be noted that the sending time of the second indication message is not limited to after the target user equipment group is determined. In a possible implementation, when (or before sending the first message, or before receiving the second message after sending the first message) the first message is sent to each candidate user equipment in the first candidate user equipment group, the network device sends a second indication message to each candidate user equipment, the second indication message being used to indicate that each candidate user equipment needs to continuously monitor whether the measurement information of each candidate user equipment meets the requirement information of the federated learning after being determined as a target user equipment.

[0150] S602, the network device receives a third indication message of a first target user equipment, the third indication message being used to indicate that the first target user equipment does not meet the requirement of the federated learning, the first target user equipment being one of the target user equipment group.

[0151] When a certain target user equipment (i.e. the first target user equipment) in the multiple target user equipments monitors that the measurement information of the first target user equipment does not meet the requirement of the federated learning, the first target user equipment sends a third indication message to the network device, the third indication message being used to indicate that the first target user equipment does not meet the requirement of the federated learning.

[0152] S603, the network device removes the first target user equipment from the target user equipment group; or, reduces the priority of the first target user equipment in the target user equipment group.

[0153] When the first target user equipment no longer satisfies the requirement information of the federated learning, the network device can remove the first target user equipment from the target user equipment group; or the network device can reduce the priority of the first target user equipment in the target user equipment group. It should be noted that removing the first target user equipment from the target user equipment group can be understood as that, in the case that the federated learning is a multi-round federated learning, the first target user equipment no longer participates in the federated learning after the current round of federated learning. Reducing the priority of the first target user equipment in the target user equipment group can be understood as that, in the case that the federated learning is a multi-round federated learning, the first target user equipment can participate in the federated learning after the current round of federated learning.

[0154] For example, the target user equipment group is UE1-UE4. The network device sends a second indication message to UE1-UE4, so that each UE in UE1-UE4 continuously monitors whether the measurement information of the UE itself satisfies the requirement information of the federated learning. If UE3 (i.e. the first target user equipment) monitors that the UE3 itself does not satisfy the requirement information of the federated learning, the UE3 sends a third indication message to the network device, the third indication message being used to indicate that the UE3 does not satisfy the requirement information of the federated learning. Further, the network device removes the UE3 from the target user equipment group, that is, it can be understood that the target user equipment group of the federated learning includes UE1, UE2 and UE4. Alternatively, the network device reduces the priority of the UE3 in the target user equipment group, which can be understood as that, in the case that the federated learning is a multi-round federated learning, if the number of target user equipments after not considering the UE3 is sufficient for the next round of federated learning, the network device does not consider the UE3 to participate in the next round of federated learning; if the number of target user equipments after not considering the UE3 is not sufficient for the next round of federated learning, the UE3 still participates in the next round of federated learning.

[0155] Please refer to Figure 7a and Figure 7b , Figure 7a and Figure 7b are flow diagrams of the optimization scheme of the user equipment selection provided by the present application. Through the method shown in Figure 7a and Figure 7b , an execution scheme is provided for the second target user equipment performing federated learning in the scenario of performing handover, which can increase the robustness of the federated learning system.

[0156] It should be noted that when performing the handover for the second target user equipment, it can be understood as the source base station of the second target user equipment receiving the measurement report of the second target user equipment, before the source base station configuring the connection parameters of the target base station for the second target user equipment; or, it can be understood as the second target user equipment receiving the connection parameters of the target base station, in the process of performing the handover; or, it can also be understood as the second target user equipment successfully switching the connection from the source base station to the target base station.

[0157] In one possible embodiment, the second target user equipment is one of the target user equipment group, and when performing the handover for the second target user equipment, the network device can keep the second target user equipment to continue participating in the federated learning. Please refer to Figure 7a as shown, wherein:

[0158] S701, the network device sends a global model to the target base station.

[0159] S702, the target base station issues the global model to the second target user equipment.

[0160] S703, the second target user equipment updates the global model to obtain updated model parameters (including model weights and gradient values).

[0161] S704, the second target user equipment sends the updated model parameters (including model weights and gradient values) to the target base station.

[0162] S705, the target base station sends the updated model parameters (including model weights and gradient values) to the network device.

[0163] In other words, in the method shown in Figure 7a after the second target user equipment switches the connection to the target base station, the network device can issue the global model to the second target user equipment through the target base station, and the second target user equipment can also send the updated model parameters to the network device through the target base station. In one possible implementation, the network device can also send the measurement information of the user equipment to the target base station, and the measurement information of the user equipment is used by the target base station to determine the first candidate user equipment group of other federated learning (or the next round of federated learning after the current round of federated learning).

[0164] In another possible embodiment, the second target user equipment is one of the target user equipment group, and when performing the handover for the second target user equipment, the network device releases the second target user equipment. Please refer to Figure 7b as shown, wherein:

[0165] S711 (optional), the network device sends a notification message to the second target user device, the notification message being used for notifying the second target user device to no longer participate in the federated learning.

[0166] It is to be known that the network device can send an explicit notification message to the second target user, notifying the second target user device to no longer participate in the federated learning. The network device can also send an implicit notification message (for example, no longer sending federated learning related messages to the second target user) to the second target user, so as to make the second target user device no longer participate in the federated learning.

[0167] S712, the network device removes the second target user device from the target user device group.

[0168] In other words, in the method shown in Figure 7b In the method shown, when the second target user device performs switching, the network device can release the second target user device, the second target user device no longer participates in the federated learning, and the second target user device is removed from the target user device group.

[0169] Please refer to Figure 8 As shown, Figure 8 An optimization scheme of user device selection is provided for the present application. By Figure 8 In the method shown, a scheme of triggering the establishment of dual connectivity is provided for the third target user device participating in the federated learning, increasing the stability of the third target user device in the federated learning.

[0170] S801, the network device sends a secondary node addition request message to a neighboring base station, the secondary node addition request message being used for establishing a communication connection between the third target user device and the neighboring base station, the third target user device being one of the target user device group.

[0171] In other words, when the network device senses that the third target user device is at the cell edge, the network device can establish dual connectivity for the third target user device, that is, send a secondary node addition request message to the neighboring base station of the network device, for the serving base station of the third target user device.

[0172] S802, the neighboring base station sends a secondary node addition request confirmation message to the network device.

[0173] The secondary node addition request confirmation message includes configuration information (including wireless connection parameters of the secondary cell, etc.) of the secondary cell corresponding to the neighboring base station.

[0174] S803, the network device sends an RRC reconfiguration message to the third target user device.

[0175] The RRC reconfiguration message includes configuration information of the secondary cell (including radio connection parameters of the secondary cell, etc.).

[0176] S804, the third target user equipment sends an RRC reconfiguration completion message to the network device.

[0177] S805, the network device sends a secondary node reconfiguration completion message to the neighboring base station.

[0178] S806, the third target user equipment randomly accesses the neighboring base station, that is, the third target user equipment can be understood as establishing a communication connection with the neighboring base station.

[0179] Further, after the neighboring base station establishes a communication connection with the third target user equipment according to the secondary node addition request message, both the network device and the neighboring base station can receive federated learning data (such as updated model parameters and gradient values) from the third target user equipment. In one possible implementation, after the neighboring base station receives the federated learning data from the third target user equipment, the neighboring base station will send the federated learning data of the third target user equipment to the network device by default. In another possible implementation, the network device sends a sixth indication message to the neighboring base station, the sixth indication message being used to indicate sending federated learning data of the third target user equipment; further, the neighboring base station sends the federated learning data of the third target user equipment to the network device according to the sixth indication message.

[0180] Please refer to Figure 9 , Figure 9 is a structural schematic diagram of a user equipment selection device provided by an embodiment of the present application. The user equipment selection device can be a network device or a device (such as a chip) having a network device function. Specifically, as shown in Figure 9 , the user equipment selection device 900 can include:

[0181] The sending unit 901 is configured to send a first message to a first candidate user equipment group; the receiving unit 902 is configured to receive a second message from a second candidate user equipment group, the first candidate user equipment group including the second candidate user equipment group; wherein the first message is used to indicate demand information of federated learning, the second message is used to indicate whether a corresponding user equipment satisfies the demand information of the federated learning, and / or measurement information of the corresponding user equipment; or, the first message is used to request measurement information of a user equipment, and the second message includes the measurement information; the demand information of the federated learning includes time length demand information of the federated learning, and / or demand information of user equipment stability of the federated learning; the determining unit 903 is configured to determine a target user equipment group participating in the federated learning based on the second message, each target user equipment in the target user equipment group satisfying the demand information of the federated learning.

[0182] In a possible implementation, the requirement information of the federated learning on the stability of the user equipment includes requirement information on mobility of the user equipment, and / or requirement information on a running state of the user equipment.

[0183] In a possible implementation, the requirement information of the federated learning on the stability of the user equipment includes one or more of the following: mobility level requirement information, location requirement information of the user equipment, computing power change rate requirement information, or signal quality change rate requirement information.

[0184] In a possible implementation, the measurement information includes one or more of the following: a mobility level, a location of the user equipment, a computing power change rate, or a signal quality change rate.

[0185] In a possible implementation, the sending unit 901 is further configured to send, to the first candidate user equipment group, a first indication message, where the first indication message is used to indicate updating the measurement information.

[0186] In a possible implementation, the first indication message includes the measurement requirement information.

[0187] In a possible implementation, the sending unit 901 is further configured to send, to the target user equipment group, a second indication message, where the second indication message is used to indicate continuously monitoring whether the requirement information of the federated learning is met; the receiving unit 902 is further configured to receive a third indication message of a first target user equipment, where the third indication message is used to indicate that the first target user equipment does not meet the requirement information of the federated learning, and the first target user equipment is one of the target user equipment group; the determining unit 903 is further configured to remove the first target user equipment from the target user equipment group; or, reduce a priority of the first target user equipment in the target user equipment group.

[0188] In a possible implementation, the second indication message further includes the requirement information of the federated learning.

[0189] In a possible implementation, the receiving unit 902 is further configured to receive a fourth indication message from another network device, where the fourth indication message is used to indicate the measurement information of at least one user equipment, and the fourth indication message is used to determine the first candidate user equipment group.

[0190] In a possible implementation, the sending unit 901 is further configured to send, to another network device, a fifth indication message, where the fifth indication message is used to indicate the measurement information of at least one user equipment.

[0191] In a possible implementation, when performing the handover for the second target user equipment, the determining unit 903 is further configured to release the second target user equipment, the second target user equipment being one of the target user equipment group; and remove the second target user equipment from the target user equipment group.

[0192] In a possible implementation, the sending unit 901 is configured to send, to the neighboring base station, a secondary node addition request message, the secondary node addition request message being used to establish a communication connection between the third target user equipment and the neighboring base station; the third target user equipment being one of the target user equipment group.

[0193] In a possible implementation, the sending unit 901 is configured to send, to the neighboring base station, a sixth indication message, the sixth indication message being used to indicate to send the federated learning data of the third target user equipment; and receive the federated learning data of the third target user equipment from the neighboring base station.

[0194] Please refer to Figure 10 , Figure 10 is a structural schematic diagram of a user equipment selection apparatus provided by an embodiment of the present application. The user equipment selection apparatus can be a user equipment or a device (for example, a chip) having a user equipment function. Specifically, as shown in Figure 10 , the user equipment selection apparatus 1000 can include:

[0195] The receiving unit 1001 is configured to receive a first message from a network device; and the sending unit 1002 is configured to send a second message to the network device; wherein the first message is used to indicate federated learning requirement information, and the second message is used to indicate whether a corresponding user equipment meets the federated learning requirement information and / or measurement information of the corresponding user equipment; or the first message is used to request measurement information of a user equipment, and the second message includes the measurement information; the federated learning requirement information includes time length requirement information of federated learning and / or requirement information of user equipment stability for federated learning.

[0196] In a possible implementation, the requirement information of user equipment stability for federated learning includes requirement information of user equipment mobility and / or requirement information of user equipment running state.

[0197] In a possible implementation, the requirement information of user equipment stability for federated learning includes one or more of the following: mobility level requirement information, location requirement information of the user equipment, calculation power change rate requirement information, or signal quality change rate requirement information.

[0198] In a possible implementation, the measurement information includes one or more of the following: mobility level, location of the user equipment, calculation power change rate, or signal quality change rate.

[0199] In a possible implementation, the receiving unit 1001 is further configured to receive a first indication message from the network device, where the first indication message is used to indicate to update the measurement information; and update the measurement information based on the first indication message.

[0200] In a possible implementation, the apparatus further includes an updating unit 1003, and the first indication message includes measurement requirement information, and the updating unit 1003 is configured to update the measurement information based on the first indication message if the user equipment does not meet the measurement requirement information.

[0201] In a possible implementation, the receiving unit 1001 is further configured to receive a second indication message from the network device, where the second indication message is used to indicate to continuously monitor whether the requirement information of the federated learning is met; and the sending unit 1002 is further configured to send a third indication message to the network device, where the third indication message is used to indicate that the user equipment does not meet the requirement information of the federated learning.

[0202] In a possible implementation, the second indication message further includes the requirement information of the federated learning.

[0203] Please refer to Figure 11 , Figure 11 is a structural diagram of a network device provided by an embodiment of the application. The network device 1100 can include a memory 1101, a processor 1102, and optionally a communication interface 1103. The memory 1101, the processor 1102 and the communication interface 1103 are connected through one or more communication buses. The communication interface 1103 is controlled by the processor 1102 to receive or send information.

[0204] The memory 1101 can include read-only memory and random access memory, and provide instructions and data for the processor 1102. A part of the memory 1101 can also include non-volatile random access memory.

[0205] The communication interface 1103 is configured to receive or send data.

[0206] The processor 1102 can be a central processing unit (CPU), and can also be other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor, and optionally, the processor 1102 can also be any conventional processor.

[0207] The memory 1101 is configured to store program instructions.

[0208] The processor 1102 is configured to invoke the program instructions stored in the memory 1101.

[0209] The processor 1102 invokes the program instructions stored in the memory 1101, so that the network device 1100 performs the following operations: sending a first message to a first candidate user equipment group; receiving a second message from a second candidate user equipment group, the first candidate user equipment group including the second candidate user equipment group; wherein the first message is used to indicate requirement information of federated learning, the second message is used to indicate whether a corresponding user equipment satisfies the requirement information of federated learning, and / or measurement information of the corresponding user equipment; or, the first message is used to request measurement information of a user equipment, and the second message includes the measurement information; the requirement information of federated learning includes time length requirement information of federated learning, and / or requirement information of user equipment stability of federated learning; based on the second message, determining a target user equipment group participating in federated learning, each target user equipment in the target user equipment group satisfying the requirement information of federated learning.

[0210] In one possible implementation, the requirement information of user equipment stability of federated learning includes requirement information of user equipment mobility, and / or requirement information of user equipment running state.

[0211] In one possible implementation, the requirement information of user equipment stability of federated learning includes one or more of the following: mobility level requirement information, location requirement information of user equipment, computing power change rate requirement information, or signal quality change rate requirement information.

[0212] In one possible implementation, the measurement information includes one or more of the following: mobility level, location of user equipment, computing power change rate, or signal quality change rate.

[0213] In a possible implementation, the processor 1102 is further configured to send a first indication message to the first candidate user equipment group, where the first indication message is used to indicate that the measurement information is updated.

[0214] In a possible implementation, the first indication message comprises measurement requirement information.

[0215] In a possible implementation, the processor 1102 is further configured to send a second indication message to the target user equipment group, where the second indication message is used to indicate that the requirement information of the federated learning is continuously monitored; receive a third indication message of a first target user equipment, where the third indication message is used to indicate that the first target user equipment does not meet the requirement information of the federated learning, and the first target user equipment is one of the target user equipment group; remove the first target user equipment from the target user equipment group; or, reduce the priority of the first target user equipment in the target user equipment group.

[0216] In a possible implementation, the second indication message further comprises the requirement information of the federated learning.

[0217] In a possible implementation, the processor 1102 is further configured to receive a fourth indication message from another network device, where the fourth indication message is used to indicate the measurement information of at least one user equipment, and the fourth indication message is used to determine the first candidate user equipment group.

[0218] In a possible implementation, the processor 1102 is further configured to send a fifth indication message to another network device, where the fifth indication message is used to indicate the measurement information of at least one user equipment.

[0219] In a possible implementation, when performing handover for a second target user equipment, the processor 1102 is further configured to release the second target user equipment, where the second target user equipment is one of the target user equipment group; and remove the second target user equipment from the target user equipment group.

[0220] In a possible implementation, the processor 1102 is configured to send a secondary node addition request message to a neighboring base station, where the secondary node addition request message is used to establish a communication connection between the third target user equipment and the neighboring base station; and the third target user equipment is one of the target user equipment group.

[0221] In a possible implementation, the processor 1102 is configured to send a sixth indication message to a neighboring base station, where the sixth indication message is used to indicate that the federated learning data of the third target user equipment is sent; and receive the federated learning data of the third target user equipment from the neighboring base station.

[0222] See Figure 12, Figure 12 is a structural schematic diagram of a user equipment provided by an embodiment of the present application. The user equipment 1200 can include a memory 1201, a processor 1202. Optionally, it also includes a communication interface 1203. The memory 1201, the processor 1202 and the communication interface 1203 are connected through one or more communication buses. Among them, the communication interface 1203 is controlled by the processor 1202 for transceiving information.

[0223] The memory 1201 can include read-only memory and random access memory, and provide instructions and data for the processor 1202. A part of the memory 1201 can also include non-volatile random access memory.

[0224] The communication interface 1203 is used to receive or send data.

[0225] The processor 1202 can be a central processing unit (CPU), and the processor 1202 can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor, and optionally, the processor 1202 can also be any conventional processor or the like. Among them:

[0226] The memory 1201 is used to store program instructions.

[0227] The processor 1202 is used to call the program instructions stored in the memory 1201.

[0228] The processor 1202 calls the program instructions stored in the memory 1201, so that the user equipment 1200 performs the following operations: receiving a first message from a network device; sending a second message to the network device; wherein the first message is used to indicate the demand information of federated learning, and the second message is used to indicate whether the corresponding user equipment meets the demand information of federated learning, and / or the measurement information of the corresponding user equipment; or, the first message is used to request the measurement information of the user equipment, and the second message includes the measurement information; the demand information of federated learning includes the time length demand information of federated learning, and / or the demand information of user equipment stability of federated learning.

[0229] In a possible implementation, the requirement information of the federated learning on the stability of the user equipment includes requirement information on mobility of the user equipment, and / or requirement information on a running state of the user equipment.

[0230] In a possible implementation, the requirement information of the federated learning on the stability of the user equipment includes one or more of the following: mobility level requirement information, location requirement information of the user equipment, computing power change rate requirement information, or signal quality change rate requirement information.

[0231] In a possible implementation, the measurement information includes one or more of the following: a mobility level, a location of the user equipment, a computing power change rate, or a signal quality change rate.

[0232] In a possible implementation, the processor 1202 is further configured to receive a first indication message from the network device, the first indication message being used to indicate to update the measurement information; and update the measurement information based on the first indication message.

[0233] In a possible implementation, the first indication message includes measurement requirement information, and the processor 1202 is configured to update the measurement information based on the first indication message if the user equipment does not meet the measurement requirement information.

[0234] In a possible implementation, the processor 1202 is further configured to receive a second indication message from the network device, the second indication message being used to indicate to continuously monitor whether the requirement information of the federated learning is met; and send a third indication message to the network device, the third indication message being used to indicate that the user equipment does not meet the requirement information of the federated learning.

[0235] In a possible implementation, the second indication message further includes the requirement information of the federated learning.

[0236] It should be noted that Figures 9-12 The content not mentioned in the corresponding embodiments and the specific implementation of each step can be referred to Figures 3-8 the embodiments shown and the foregoing, which will not be repeated here.

[0237] The embodiment of the application further provides a chip which can execute the related steps of the network device in the foregoing method embodiment. The chip comprises a processor and a communication interface, and the processor is configured to perform the following operations: sending a first message to a first candidate user equipment group; receiving a second message from a second candidate user equipment group, the first candidate user equipment group comprising the second candidate user equipment group; wherein the first message is used for indicating requirement information of federated learning, the second message is used for indicating whether a corresponding user equipment satisfies the requirement information of federated learning and / or measurement information of the corresponding user equipment; or the first message is used for requesting measurement information of a user equipment, and the second message comprises the measurement information; the requirement information of federated learning comprises time length requirement information of federated learning and / or requirement information of user equipment stability of federated learning; and based on the second message, determining a target user equipment group participating in federated learning, each target user equipment in the target user equipment group satisfying the requirement information of federated learning.

[0238] In a possible implementation, the requirement information of user equipment stability of federated learning comprises requirement information of user equipment mobility and / or requirement information of user equipment running state.

[0239] In a possible implementation, the requirement information of user equipment stability of federated learning comprises one or more of the following: mobility level requirement information, location requirement information of user equipment, computing power change rate requirement information or signal quality change rate requirement information.

[0240] In a possible implementation, the measurement information comprises one or more of the following: mobility level, location of user equipment, computing power change rate or signal quality change rate.

[0241] In a possible implementation, the processor is further configured to send a first indication message to the first candidate user equipment group, the first indication message being used for indicating that the measurement information is updated.

[0242] In a possible implementation, the first indication message comprises measurement requirement information.

[0243] In a possible implementation, the processor is further configured to send a second indication message to the target user equipment group, the second indication message being used for indicating whether the requirement information of federated learning is satisfied by continuous monitoring; receive a third indication message of a first target user equipment, the third indication message being used for indicating that the first target user equipment does not satisfy the requirement information of federated learning, the first target user equipment being one of the target user equipment group; remove the first target user equipment from the target user equipment group; or reduce the priority of the first target user equipment in the target user equipment group.

[0244] In a possible implementation, the second indication message further includes demand information of the federated learning.

[0245] In a possible implementation, the processor is further configured to receive a fourth indication message from the other network device, the fourth indication message being used to indicate the measurement information of the at least one user equipment, and the fourth indication message being used to determine the first candidate user equipment group.

[0246] In a possible implementation, the processor is further configured to send a fifth indication message to the other network device, the fifth indication message being used to indicate the measurement information of the at least one user equipment.

[0247] In a possible implementation, when performing handover for a second target user equipment, the processor is further configured to release the second target user equipment, the second target user equipment being one of the target user equipment group; and remove the second target user equipment from the target user equipment group.

[0248] In a possible implementation, the processor is configured to send a secondary node addition request message to the neighboring base station, the secondary node addition request message being used to establish a communication connection between a third target user equipment and the neighboring base station, the third target user equipment being one of the target user equipment group.

[0249] In a possible implementation, the processor is configured to send a sixth indication message to the neighboring base station, the sixth indication message being used to indicate federated learning data of the third target user equipment; and receive the federated learning data of the third target user equipment from the neighboring base station.

[0250] Embodiments of the present application further provide a chip, which can perform the related steps of the user equipment in the foregoing method embodiments. The chip includes a processor and a communication interface, and the processor is configured to perform the following operations: receiving a first message from a network device; and sending a second message to the network device; wherein the first message is used to indicate demand information of federated learning, and the second message is used to indicate whether a corresponding user equipment meets the demand information of the federated learning, and / or measurement information of the corresponding user equipment; or the first message is used to request measurement information of the user equipment, and the second message includes the measurement information; and the demand information of the federated learning includes time length demand information of the federated learning, and / or demand information of user equipment stability of the federated learning.

[0251] In a possible implementation, the demand information of user equipment stability of the federated learning includes demand information of user equipment mobility, and / or demand information of user equipment running state.

[0252] In one possible implementation, the information required by federated learning for user equipment stability includes one or more of the following: mobility level requirements, user equipment location requirements, computing power change rate requirements, or signal quality change rate requirements.

[0253] In one possible implementation, the measurement information includes one or more of the following: mobility level, location of user equipment, rate of change of computing power, or rate of change of signal quality.

[0254] In one possible implementation, the processor is further configured to receive a first indication message from a network device, the first indication message being used to indicate updating measurement information; and to update the measurement information based on the first indication message.

[0255] In one possible implementation, the first indication message includes measurement requirement information, and the processor is configured to update the measurement information based on the first indication message if the user equipment does not meet the measurement requirement information.

[0256] In one possible implementation, the processor is further configured to receive a second indication message from the network device, the second indication message indicating whether the requirements for federated learning are being continuously monitored; and to send a third indication message to the network device, the third indication message indicating that the user equipment does not meet the requirements for federated learning.

[0257] In one possible implementation, the second instruction message may also include information on the requirements for federated learning.

[0258] like Figure 13 As shown, Figure 13 This is a schematic diagram of the structure of a module device provided in an embodiment of this application. The module device 1300 can perform the relevant steps of the user equipment in the aforementioned method embodiments. The module device 1300 includes: a communication module 1301, a power module 1302, a storage module 1303, and a chip 1304.

[0259] The power module 1302 provides power to the module device; the storage module 1303 stores data and instructions; the communication module 1301 performs internal communication within the module device or allows the module device to communicate with external devices; and the chip 1304 is used for:

[0260] sending a first message to a first candidate user equipment group, the first candidate user equipment group comprising a second candidate user equipment group; receiving a second message from the second candidate user equipment group, the first message being used to indicate requirement information of federated learning, the second message being used to indicate whether a corresponding user equipment satisfies the requirement information of the federated learning and / or measurement information of the corresponding user equipment; or, the first message being used to request measurement information of a user equipment, the second message comprising the measurement information; the requirement information of the federated learning comprising time length requirement information of the federated learning and / or requirement information of user equipment stability of the federated learning; determining a target user equipment group participating in the federated learning based on the second message, each target user equipment in the target user equipment group satisfying the requirement information of the federated learning.

[0261] In a possible implementation, the requirement information of user equipment stability of the federated learning comprises requirement information of user equipment mobility and / or requirement information of user equipment running state.

[0262] In a possible implementation, the requirement information of user equipment stability of the federated learning comprises one or more of the following: mobility level requirement information, location requirement information of the user equipment, computing power change rate requirement information or signal quality change rate requirement information.

[0263] In a possible implementation, the measurement information comprises one or more of the following: mobility level, location of the user equipment, computing power change rate or signal quality change rate.

[0264] In a possible implementation, the chip 1304 is further configured to send a first indication message to the first candidate user equipment group, the first indication message being used to indicate updating the measurement information.

[0265] In a possible implementation, the first indication message comprises measurement requirement information.

[0266] In a possible implementation, the chip 1304 is further configured to send a second indication message to the target user equipment group, the second indication message being used to indicate whether the requirement information of the federated learning is satisfied; receive a third indication message of a first target user equipment, the third indication message being used to indicate that the first target user equipment does not satisfy the requirement information of the federated learning, the first target user equipment being one of the target user equipment group; remove the first target user equipment from the target user equipment group; or, reduce a priority of the first target user equipment in the target user equipment group.

[0267] In a possible implementation, the second indication message further comprises the requirement information of the federated learning.

[0268] In a possible implementation, the chip 1304 is further configured to receive a fourth indication message from another network device, the fourth indication message being used to indicate measurement information of at least one user equipment, and the fourth indication message being used to determine the first candidate user equipment group.

[0269] In a possible implementation, the chip 1304 is further configured to send a fifth indication message to another network device, the fifth indication message being used to indicate measurement information of at least one user equipment.

[0270] In a possible implementation, when performing handover for a second target user equipment, the chip 1304 is further configured to release the second target user equipment, the second target user equipment being one of the target user equipment group; and remove the second target user equipment from the target user equipment group.

[0271] In a possible implementation, the chip 1304 is configured to send a secondary node addition request message to a neighboring base station, the secondary node addition request message being used to establish a communication connection between a third target user equipment and the neighboring base station, and the third target user equipment being one of the target user equipment group.

[0272] In a possible implementation, the chip 1304 is configured to send a sixth indication message to a neighboring base station, the sixth indication message being used to indicate federated learning data of a third target user equipment, and receive federated learning data of the third target user equipment from the neighboring base station.

[0273] In an embodiment, Figure 13 The chip 1304 in the module device shown can also be configured to: receive a first message from a network device; and send a second message to the network device, wherein the first message is used to indicate federated learning requirement information, and the second message is used to indicate whether a corresponding user equipment meets the federated learning requirement information and / or measurement information of the corresponding user equipment; or the first message is used to request measurement information of a user equipment, and the second message includes the measurement information; and the federated learning requirement information includes time length requirement information of the federated learning and / or requirement information of user equipment stability for the federated learning.

[0274] In a possible implementation, the requirement information of user equipment stability for the federated learning includes requirement information of mobility of the user equipment and / or requirement information of a running state of the user equipment.

[0275] In a possible implementation, the requirement information of user equipment stability for the federated learning includes one or more of the following: mobility level requirement information, location requirement information of the user equipment, calculation power change rate requirement information, or signal quality change rate requirement information.

[0276] In a possible implementation, the measurement information comprises one or more of the following: a mobility level, a location of the user equipment, a change rate of computing power, or a change rate of signal quality.

[0277] In a possible implementation, the chip 1304 is further configured to receive a first indication message from the network device, the first indication message being used to indicate to update the measurement information; and update the measurement information based on the first indication message.

[0278] In a possible implementation, the first indication message comprises measurement requirement information, and the chip 1304 is configured to update the measurement information based on the first indication message if the user equipment does not meet the measurement requirement information.

[0279] In a possible implementation, the chip 1304 is further configured to receive a second indication message from the network device, the second indication message being used to indicate to continuously monitor whether the requirement information of the federated learning is met; and send a third indication message to the network device, the third indication message being used to indicate that the user equipment does not meet the requirement information of the federated learning.

[0280] In a possible implementation, the second indication message further comprises the requirement information of the federated learning.

[0281] The embodiments of the present application further provide a computer readable storage medium, which stores instructions, when the instructions are run on a processor, the method flow of the method embodiments is realized.

[0282] The embodiments of the present application further provide a computer program product, when the computer program product is run on a processor, the method flow of the method embodiments is realized.

[0283] It should be noted that, for the foregoing method embodiments, the sequences of the described actions are not necessarily required to implement the application and some of the actions can be performed in other sequences, or even at the same time. Additionally, it should be noted that described embodiments are to be considered as illustrative only and not restrictive in character, as some of the actions and modules involved are not required for the application.

[0284] It should be noted that, for the foregoing method embodiments, the sequences of the described actions are not necessarily required to implement the application and some of the actions can be performed in other sequences, or even at the same time. Additionally, it should be noted that described embodiments are to be considered as illustrative only and not restrictive in character, as some of the actions and modules involved are not required for the application.

[0285] The descriptions of the various embodiments provided by the application can be mutually referred to, and the descriptions of the various embodiments each have a focus. The parts not described in detail in a certain embodiment can be referred to the relevant descriptions of other embodiments. For the convenience and brevity of description, for example, the functions of the various devices and the operations performed by the devices provided by the embodiments of the application can be referred to the relevant descriptions of the method embodiments of the application, and the method embodiments and the device embodiments can be referred to, combined, or cited to each other.

[0286] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for selecting user equipment, characterized in that, The method includes: Send the first message to the first candidate user equipment group; Receive a second message from a second candidate user equipment group, wherein the first candidate user equipment group includes the second candidate user equipment group; Wherein, the first message is used to indicate the requirements information for federated learning, the second message is used to indicate whether the corresponding user equipment meets the requirements information for federated learning, and / or the measurement information of the corresponding user equipment; Alternatively, the first message may be used to request measurement information from the user equipment, and the second message may include the measurement information; the federated learning requirement information may include the federated learning's requirement information for the stability of the user equipment. The federated learning's requirements for user equipment stability include one or more of the following: mobility level requirements, user equipment location requirements, computing power change rate requirements, or signal quality change rate requirements; the measurement information includes one or more of the following: mobility level, user equipment location, computing power change rate, or signal quality change rate. Based on the second message, a target user equipment group is determined to participate in the federated learning, and each target user equipment in the target user equipment group meets the requirements of the federated learning.

2. The method according to claim 1, characterized in that, The federated learning's requirements for user equipment stability include requirements for user equipment mobility and / or requirements for user equipment operational status.

3. The method according to claim 1 or 2, characterized in that, Before receiving the second message from the second candidate user equipment group, the method further includes: A first indication message is sent to the first candidate user equipment group, the first indication message being used to indicate the updating of the measurement information.

4. The method according to claim 3, characterized in that, The first instruction message includes measurement requirement information.

5. The method according to any one of claims 1-4, characterized in that, The method further includes: Send a second instruction message to the target user equipment group, the second instruction message being used to instruct continuous monitoring of whether the requirements for federated learning are met; A third indication message is received from a first target user device, the third indication message indicating that the first target user device does not meet the requirements of the federated learning; the first target user device is one of the target user device groups. Remove the first target user equipment from the target user equipment group; or, reduce the priority of the first target user equipment in the target user equipment group.

6. The method according to claim 5, characterized in that, The second instruction message also includes the requirement information for the federated learning.

7. The method according to claim 1, characterized in that, The method further includes: A fourth indication message is received from other network devices, the fourth indication message being used to indicate the measurement information of at least one user equipment, the fourth indication message being used to determine the first candidate user equipment group.

8. The method according to claim 1, characterized in that, The method further includes: A fifth indication message is sent to other network devices, the fifth indication message being used to indicate the measurement information of at least one user device.

9. The method according to any one of claims 1-8, characterized in that, The method further includes: When performing a handover for a second target user equipment, the second target user equipment is released; the second target user equipment is one of the target user equipment groups. Remove the second target user equipment from the target user equipment group.

10. The method according to any one of claims 1-5, characterized in that, The method further includes: A secondary node add request message is sent to a neighboring base station. The secondary node add request message is used to establish a communication connection between the third target user equipment and the neighboring base station. The third target user equipment is one of the target user equipment groups.

11. The method according to claim 10, characterized in that, The method further includes: Send a sixth indication message to the neighboring base station, the sixth indication message being used to indicate the transmission of federated learning data of the third target user equipment; Receive federated learning data from the third target user equipment from the neighboring base station.

12. A method for selecting user equipment, characterized in that, The method includes: Receive the first message from the network device; Send a second message to the network device; Wherein, the first message is used to indicate the requirements information of federated learning, the second message is used to indicate whether the corresponding user equipment meets the requirements information of federated learning, and / or the measurement information of the corresponding user equipment; or, the first message is used to request the measurement information of the user equipment, and the second message includes the measurement information; the requirements information of federated learning includes the requirements information of federated learning on the stability of the user equipment; The federated learning's requirements for user equipment stability include one or more of the following: mobility level requirements, user equipment location requirements, computing power change rate requirements, or signal quality change rate requirements; the measurement information includes one or more of the following: mobility level, user equipment location, computing power change rate, or signal quality change rate.

13. The method according to claim 12, characterized in that, The federated learning's requirements for user equipment stability include requirements for user equipment mobility and / or requirements for user equipment operational status.

14. The method according to claim 12 or 13, characterized in that, Before sending the second message to the network device, the method further includes: Receive a first indication message from the network device, the first indication message being used to indicate updating the measurement information; Update the measurement information based on the first indication message.

15. The method according to claim 14, characterized in that, The first indication message includes measurement requirement information, and the step of updating the measurement information based on the first indication message includes: If the user equipment does not meet the measurement requirement information, the measurement information is updated based on the first indication message.

16. The method according to any one of claims 12-15, characterized in that, The method further includes: Receive a second indication message from the network device, the second indication message being used to indicate whether the requirements for federated learning are met through continuous monitoring; A third indication message is sent to the network device, the third indication message being used to indicate that the user equipment does not meet the requirements of the federated learning.

17. The method according to claim 16, characterized in that, The second instruction message also includes the requirement information for the federated learning.

18. A user equipment selection device, characterized in that, The device includes: The sending unit is used to send a first message to the first candidate user equipment group; A receiving unit is configured to receive a second message from a second candidate user equipment group, wherein the first candidate user equipment group includes the second candidate user equipment group. Wherein, the first message is used to indicate the requirements information of federated learning, the second message is used to indicate whether the corresponding user equipment meets the requirements information of federated learning, and / or the measurement information of the corresponding user equipment; or, the first message is used to request the measurement information of the user equipment, and the second message includes the measurement information; the requirements information of federated learning includes the requirements information of federated learning on the stability of the user equipment; The federated learning's requirements for user equipment stability include one or more of the following: mobility level requirements, user equipment location requirements, computing power change rate requirements, or signal quality change rate requirements; the measurement information includes one or more of the following: mobility level, user equipment location, computing power change rate, or signal quality change rate. The determining unit is configured to determine, based on the second message, a target user equipment group participating in the federated learning, wherein each target user equipment in the target user equipment group meets the requirements information of the federated learning.

19. A user equipment selection device, characterized in that, The device includes: The receiving unit is used to receive the first message from the network device; A sending unit is used to send a second message to the network device; Wherein, the first message is used to indicate the requirements information of federated learning, the second message is used to indicate whether the corresponding user equipment meets the requirements information of federated learning, and / or the measurement information of the corresponding user equipment; or, the first message is used to request the measurement information of the user equipment, and the second message includes the measurement information; the requirements information of federated learning includes the requirements information of federated learning on the stability of the user equipment; The federated learning's requirements for user equipment stability include one or more of the following: mobility level requirements, user equipment location requirements, computing power change rate requirements, or signal quality change rate requirements; the measurement information includes one or more of the following: mobility level, user equipment location, computing power change rate, or signal quality change rate.

20. A chip, characterized in that, Includes a processor and a communication interface, the processor being configured to perform the following operations: Send the first message to the first candidate user equipment group; Receive a second message from a second candidate user equipment group, wherein the first candidate user equipment group includes the second candidate user equipment group; Wherein, the first message is used to indicate the requirements information of federated learning, the second message is used to indicate whether the corresponding user equipment meets the requirements information of federated learning, and / or the measurement information of the corresponding user equipment; or, the first message is used to request the measurement information of the user equipment, and the second message includes the measurement information; the requirements information of federated learning includes the requirements information of federated learning on the stability of the user equipment; The federated learning's requirements for user equipment stability include one or more of the following: mobility level requirements, user equipment location requirements, computing power change rate requirements, or signal quality change rate requirements; the measurement information includes one or more of the following: mobility level, user equipment location, computing power change rate, or signal quality change rate. Based on the second message, a target user equipment group is determined to participate in the federated learning, and each target user equipment in the target user equipment group meets the requirements of the federated learning.

21. A chip, characterized in that, Includes a processor and a communication interface, the processor being configured to perform the following operations: Receive the first message from the network device; Send a second message to the network device; Wherein, the first message is used to indicate the requirements information of federated learning, the second message is used to indicate whether the corresponding user equipment meets the requirements information of federated learning, and / or the measurement information of the corresponding user equipment; or, the first message is used to request the measurement information of the user equipment, and the second message includes the measurement information; the requirements information of federated learning includes the requirements information of federated learning on the stability of the user equipment; The federated learning's requirements for user equipment stability include one or more of the following: mobility level requirements, user equipment location requirements, computing power change rate requirements, or signal quality change rate requirements; the measurement information includes one or more of the following: mobility level, user equipment location, computing power change rate, or signal quality change rate.

22. A module device, characterized in that, The module device includes a communication module, a power module, a storage module, and a chip, wherein: The power module is used to provide electrical energy to the module device; The storage module is used to store data and instructions; The communication module is used for internal communication within the module device, or for communication between the module device and external devices; The chip is used to: send a first message to a first candidate user equipment group; Receive a second message from a second candidate user equipment group, wherein the first candidate user equipment group includes the second candidate user equipment group; Wherein, the first message is used to indicate the requirements information of federated learning, the second message is used to indicate whether the corresponding user equipment meets the requirements information of federated learning, and / or the measurement information of the corresponding user equipment; or, the first message is used to request the measurement information of the user equipment, and the second message includes the measurement information; the requirements information of federated learning includes the requirements information of federated learning on the stability of the user equipment; The federated learning's requirements for user equipment stability include one or more of the following: mobility level requirements, user equipment location requirements, computing power change rate requirements, or signal quality change rate requirements; the measurement information includes one or more of the following: mobility level, user equipment location, computing power change rate, or signal quality change rate. Based on the second message, a target user equipment group is determined to participate in the federated learning, and each target user equipment in the target user equipment group meets the requirements of the federated learning.

23. A module device, characterized in that, The module device includes a communication module, a power module, a storage module, and a chip, wherein: The power module is used to provide electrical energy to the module device; The storage module is used to store data and instructions; The communication module is used for internal communication within the module device, or for communication between the module device and external devices; The chip is used to: receive a first message from a network device; Send a second message to the network device; Wherein, the first message is used to indicate the requirements information of federated learning, the second message is used to indicate whether the corresponding user equipment meets the requirements information of federated learning, and / or the measurement information of the corresponding user equipment; or, the first message is used to request the measurement information of the user equipment, and the second message includes the measurement information; the requirements information of federated learning includes the requirements information of federated learning on the stability of the user equipment; The federated learning's requirements for user equipment stability include one or more of the following: mobility level requirements, user equipment location requirements, computing power change rate requirements, or signal quality change rate requirements; the measurement information includes one or more of the following: mobility level, user equipment location, computing power change rate, or signal quality change rate.

24. A network device, characterized in that, The device includes a memory and a processor, the memory being used to store a computer program, the computer program including program instructions, and the processor being configured to invoke the program instructions to perform the method as described in any one of claims 1 to 11.

25. A user equipment, characterized in that, The device includes a memory and a processor, the memory being used to store a computer program, the computer program including program instructions, and the processor being configured to invoke the program instructions to perform the method as described in any one of claims 12 to 17.

26. A computer-readable storage medium, characterized in that, The computer storage medium stores computer-readable instructions that, when executed on the communication device, cause the communication device to perform the method of any one of claims 1 to 11 or the method of any one of claims 12 to 17.

Images