DEVICE DETERMINATION METHOD, COMMUNICATION DEVICE, AND READABLE STORAGE MEDIUM - Patent application

Abstract

The present application discloses a device determination method, an apparatus, and a communication device. The device determination method includes the steps of: a first communication device transmitting a first request message to a second communication device to request acquisition of network performance analysis information; and the first communication device receiving, from the second communication device, network performance analysis information corresponding to M candidate devices. The network performance analysis information corresponding to one candidate device includes at least one of: radio access method information of the one candidate device; time information of the one candidate device available for participating in federated learning; location information of the one candidate device; time period information covered by the network of the one candidate device; information on a ratio of the time period covered by the network of the one candidate device within a time period of interest to the time period of interest; and network signal quality information of the one candidate device.

Description

[Technical field]

[0001] The present application relates to the technical field of communications, and in particular to a device determination method, apparatus and communication device. [Background technology]

[0002] With the development of communication technology, federated learning has emerged. Federated learning includes horizontal federated learning and vertical federated learning. Horizontal federated learning increases the number of training samples by federating the features of the same data of different samples of participating devices, while vertical federated learning increases the feature dimension of training samples by federating the features of different data of common samples of participating devices, thereby obtaining a better model.

[0003] "Component selection" is the most important factor for federated learning. By selecting an appropriate device (e.g., User Equipment (UE), etc.) to perform federated learning, the efficiency of training can be improved. Conversely, selecting an inappropriate device for federated learning will have a negative impact on the efficiency and results of training. Take the case where a consumer service device (e.g., Application Function (AF)) performs federated learning as an example. The AF can select several devices in a certain area (e.g., a certain region or a certain cell) based on the network performance corresponding to the area reported by the Network Data Analytics Function (NWDAF) to perform federated learning. However, since there is a difference in the network performance corresponding to different devices in the same area, how to select appropriate devices to participate in federated learning is an issue that must be resolved immediately. Summary of the Invention [Problem to be solved by the invention]

[0004] The embodiments of the present application provide a device determination method, an apparatus, and a communication device capable of selecting an appropriate device to participate in federated learning. [Means for solving the problem]

[0005] In a first aspect, a device determination method is provided, comprising: a step of a first communication device sending a first request message to a second communication device to request to obtain network performance analysis information; and a step of the first communication device receiving network performance analysis information from the second communication device, wherein the network performance analysis information includes network performance analysis information corresponding to M candidate devices, where M is a positive integer, and the network performance analysis information corresponding to one candidate device includes at least one type of information: radio access method information of the one candidate device, time information during which the one candidate device can participate in federated learning, location information of the one candidate device, time period information covered by the network of the one candidate device, ratio information of the time period covered by the network of the one candidate device within a time period of interest to the time period of interest, and network signal quality information of the one candidate device.

[0006] In a second aspect, a device determination method is provided, the method including: a step of a second communication device receiving a first request message from a first communication device to request to obtain network performance analysis information; and a step of the second communication device transmitting network performance analysis information to the first communication device, the network performance analysis information including network performance analysis information corresponding to M candidate devices, where M is a positive integer, and the network performance analysis information corresponding to one candidate device includes at least one type of information: radio access method information of the one candidate device, time information during which the one candidate device can participate in federated learning, location information of the one candidate device, time period information covered by the network of the one candidate device, ratio information of the time period covered by the network of the one candidate device within a time period of interest to the time period of interest, and network signal quality information of the one candidate device.

[0007] In a third aspect, a device determination device is provided, the device determination device including: a transmitting module for transmitting a first request message to a second communication device to request the second communication device to obtain network performance analysis information; and a receiving module for receiving network performance analysis information from the second communication device, the network performance analysis information including network performance analysis information corresponding to M candidate devices, where M is a positive integer, and the network performance analysis information corresponding to one candidate device includes at least one type of information: radio access method information of the one candidate device, time information of the one candidate device available for participating in federated learning, location information of the one candidate device, time period information covered by the network of the one candidate device, ratio information of the time period covered by the network of the one candidate device within a time period of interest to the time period of interest, and network signal quality information of the one candidate device.

[0008] In a fourth aspect, a device determination device is provided, the device determination device including: a receiving unit for receiving a first request message from a first communication device to request to obtain network performance analysis information; and a transmitting unit for transmitting network performance analysis information to the first communication device, the network performance analysis information including network performance analysis information corresponding to M candidate devices, where M is a positive integer, and the network performance analysis information corresponding to one candidate device includes at least one type of information: radio access method information of the one candidate device, time information of the one candidate device available for participating in federated learning, location information of the one candidate device, time period information covered by the network of the one candidate device, ratio information of the time period covered by the network of the one candidate device within a time period of interest to the time period of interest, and network signal quality information of the one candidate device.

[0009] In a fifth aspect, there is provided a communications device including a processor and a memory, wherein a program or command executable by the processor is stored in the memory, and when the program or command is executed by the processor, steps of the device determination method described in the first or second aspect are realized.

[0010] In a sixth aspect, a communication device is provided, the communication device including a processor and a communication interface, wherein when the communication device is a first communication device, the communication interface is for sending a first request message to a second communication device and receiving network performance analysis information from the second communication device, and when the communication device is the second communication device, the communication interface is for receiving the first request message from the first communication device and sending network performance analysis information to the first communication device, the network performance analysis information includes network performance analysis information corresponding to M candidate devices, M is a positive integer, and the network performance analysis information corresponding to one candidate device includes at least one type of information: radio access method information of the one candidate device, time information during which the one candidate device can participate in federated learning, location information of the one candidate device, time period information covered by the network of the one candidate device, ratio information of the time period covered by the network of the one candidate device within a time period of interest to the time period of interest, and network signal quality information of the one candidate device.

[0011] In a seventh aspect, there is provided a readable storage medium having stored thereon a program or command which, when executed by a processor, causes the steps of the device determination method according to the first or second aspect to be realized.

[0012] In an eighth aspect, there is provided a chip including a coupled processor and a communication interface, the processor being configured to execute a program or command to realize steps of the device determination method described in the first or second aspect.

[0013] In a ninth aspect, there is provided a computer program / program product that is stored in a storage medium and that, when executed by at least one processor, implements the steps of the device determination method according to the first or second aspect. Effect of the Invention

[0014] In an embodiment of the present application, a first communication device sends a first request message to a second communication device to request to obtain network performance analysis information, and the first communication device receives the network performance analysis information from the second communication device, where the network performance analysis information includes network performances corresponding to M candidate devices, where M is a positive integer. The network performance analysis information corresponding to one candidate device includes at least one of the following information: radio access method information of the one candidate device, time information of the one candidate device that can participate in federated learning, location information of the one candidate device, time period information covered by the network of the one candidate device, ratio information of the time period covered by the network of the one candidate device within the time period of interest to the time period of interest, and network signal quality information of the one candidate device. With this technical means, the wireless access method information of the device, the time information available for participating in federated learning, location information, time period information covered by the network, ratio information of the time period covered by the network to the time of interest, and network signal quality information can all reflect the network performance corresponding to the device, so that when the first communication device receives the network performance analysis information, it can determine the network performance corresponding to each candidate device among the M candidate devices, so that the first communication device can determine the candidate devices that meet the network performance requirements of the federated learning as the devices to participate in the federated learning, that is, the first communication device can select appropriate devices to participate in the federated learning. [Brief description of the drawings]

[0015] [Figure 1] 1 is a schematic flowchart of a device determination method provided in an embodiment of the present application; [Diagram 2] 1 is a schematic diagram of a device determination method provided in an embodiment of the present application. [Diagram 3] FIG. 2 is a second schematic diagram of a device determination method provided in an embodiment of the present application. [Figure 4]1 is a structural schematic diagram of a device determination apparatus provided in an embodiment of the present application; [Diagram 5] 2 is a second structural schematic diagram of a device determination apparatus provided in an embodiment of the present application; [Figure 6] FIG. 2 is a structural schematic diagram of a communication device provided in an embodiment of the present application; [Figure 7] FIG. 2 is a hardware schematic diagram of a communication device provided in an embodiment of the present application. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0016] Hereinafter, the technical solutions in the embodiments of the present application will be clearly described with reference to the drawings in the embodiments of the present application, and it is to be understood that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art shall fall within the scope of protection of the present application.

[0017] In the specification and claims of the embodiments of the present application, technical terms such as "first", "second", etc. are not intended to describe a particular order of objects, but are intended to distinguish between different objects. Note that the terms used in this manner may be interchangeable in some cases, so that the embodiments of the present application may be implemented in an order other than that shown or described herein. The objects distinguished by "first" and "second" are generally similar, and the number of objects is not limited, for example, there may be one or more first communication devices. Also, in the specification and claims, "and / or" refers to at least one of the objects connected, and the symbol " / " generally refers to the related objects before and after being in an "or" relationship.

[0018] It should be noted that the techniques described in the embodiments of the present application are not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, and may also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA), and other systems. In the embodiments of the present application, the terms "system" and "network" are often used interchangeably, and the techniques described herein may be used in the above systems and wireless communication technologies, or in other systems and wireless communication technologies. However, for illustrative purposes, the following description will describe a New Radio (NR) system, and NR terminology will be used in most of the following description, but these technologies may be applied to systems other than NR systems, such as 6th Generation (6G) communication systems.

[0019] The communication devices described in the embodiments of the present application (e.g., the first communication device, the second communication device, the third communication device, the fourth communication device, and the fifth communication device, etc.) may be core network devices and may be referred to as network elements or network nodes.A core network device is a core network node, a core network function, an application function (AF), a network data analytics function (NWDAF), a unified data management (UDM), a network exposure function (NEF), a local NEF (Local NEF or L-NEF), an operation administration and maintenance (OAM), a user plane function (UPF), a session management function (SMF), a data collection application function (DC-AF), a mobility management entity (MME), an access and mobility management function (AMF), a user plane function (UPF), a policy control function (PCF), a policy and charging rules function (PCRF), an edge application server discovery function (EASDF), a unified data repository (UDM), a network access control function (NCF), a network access control function (NCC), a network access control function (NCS ... The network may include, but is not limited to, at least one of a Home Subscriber Server (UDR), a Home Subscriber Server (HSS), a Centralized network configuration (CNC), a Network Repository Function (NRF), a Binding Support Function (BSF), and the like.In the embodiments of the present application, a core network device in an NR system is used as an example, but the specific type of the core network device is not limited.

[0020] Candidate devices in the embodiments of the present application may include terminals (which may be called terminal devices or user equipment (UE)), or any other feasible devices. The terminals may be terminal-side devices such as mobile phones, tablet personal computers, laptop computers (also called notebook computers), personal digital assistants (PDA), personal digital assistants, netbooks, ultra-mobile personal computers (UMPC), mobile internet devices (MID), augmented reality (AR) / virtual reality (VR) devices, robots, wearable devices, vehicle-mounted equipment (VUE), pedestrian terminals (PUE), smart home devices (household devices with wireless communication capabilities, such as refrigerators, televisions, washing machines, furniture, etc.), game consoles, personal computers (PC), automated teller machines, or kiosks. Wearable devices include smart watches, smart bracelets, smart earphones, smart glasses, smart accessories (smart bangles, smart hand chains, smart rings, smart necklaces, smart anklets, smart wristbands, smart clothing, etc.) In addition, in the embodiments of the present application, the specific type of terminal is not limited.

[0021] Next, the device determination method provided by the embodiments of the present application will be described in detail based on the embodiments and their application scenarios with reference to the drawings.

[0022] As shown in FIG. 1, an embodiment of the present application provides a device determination method that may include steps 201 to 204 described below.

[0023] In step 201, the first communication device sends a first request message to the second communication device.

[0024] In step 202, the second communication device receives a first request message from the first communication device.

[0025] The first request message may be for requesting to obtain network performance analysis information.

[0026] In step 203, the second communication device transmits network performance analysis information to the first communication device.

[0027] In step 204, the first communication device receives network performance analysis information from the second communication device.

[0028] The network performance analysis information may include network performance analysis information corresponding to M candidate devices, where M is a positive integer. The network performance analysis information corresponding to one candidate device may include: a) radio access method information of the one candidate device; b) Time information of the candidate device that can participate in the federated learning; and c) location information of the one candidate device; d) time period information covered by the network of the one candidate device; and e) percentage information of a time period covered by the network of the one candidate device during the time period of interest; and f) network signal quality information of the one candidate device.

[0029] In an embodiment of the present application, after receiving the first request message, the second communication device may send network performance analysis information corresponding to the M candidate devices to the first communication device, so that the first communication device obtains network performance of each candidate device among the M candidate devices, and further determines a candidate device that meets the network performance requirements of the federated learning as a device to participate in the federated learning, that is, the first communication device can select suitable candidate devices for federated learning.

[0030] In an embodiment of the present application, the network performance analysis information can indicate network performance corresponding to M candidate devices, so that when the first communication device receives the network performance analysis information, it can obtain network performance corresponding to each of the M candidate devices, and determine the candidate devices that meet the network performance requirements of the federated learning as the devices to participate in the federated learning.

[0031] In the embodiment of the present application, the first communication device may include an AF or any other possible consumer service entity, the second communication device may include an NWDAF, and the candidate device may include a UE or any other possible device. Specifically, it can be determined according to the needs of actual use, and the embodiment of the present application is not limited thereto.

[0032] In the embodiments of the present application, the radio access scheme may be a non-third generation partnership project (non 3GPP®) radio access scheme, such as wireless local area networks (WLAN), or a 3GPP® radio access designation, such as fourth generation (4G) evolved universal terrestrial radio access network (EUTRAN or E-UTRAN), fifth generation (5G) NR, etc.

[0033] For example, with respect to the above a), the radio access method information of one candidate device may indicate that the radio access method of the candidate device is non-3GPP (registered trademark) WLAN.

[0034] In an embodiment of the present application, with regard to the above b), the time information of one candidate device during which the candidate device can participate in federated learning may indicate the time during which the candidate device can participate in federated learning, for example, 00:00-04:00 every day.

[0035] In the embodiment of the present application, with regard to c) above, the location information of a candidate device may indicate the region, cell or tracking area (TA) in which the candidate device is located.

[0036] In an embodiment of the present application, the interest time may be a time that the first communication device is interested in, such as a time when the first communication device is scheduled to perform federated learning. For example, the time when the first communication device is scheduled to perform federated learning is 01:00-03:00 on March 15, 2020.

[0037] Regarding d) above, the time period information covered by the network of one candidate device may indicate the length of time or the time period covered by the network of the candidate device.

[0038] Regarding e) above, information on the proportion of the time period covered by the network of a candidate device within the time of interest relative to the time of interest (hereinafter simply referred to as proportion information of the time covered by the network) may indicate the ratio between the length of time covered by the network of the candidate device within the time of interest and the length of time corresponding to the time of interest.

[0039] As an example, if the candidate device is a terminal and the wireless access method is Wireless Local Area Networks (WLAN), the time of interest is three hours from 8:00 to 11:00, and the terminal is covered by Wireless-Fidelity (Wi-Fi) for two of these three hours, then the proportion of the time period covered by Wi-Fi for the terminal to the time of interest is 2 / 3.

[0040] Alternatively, in the embodiment of the present application, the network coverage time ratio information may indicate the ratio of the time period covered by the network of the candidate device to the time of interest according to a level, for example, but not limited to, "high, medium, low", etc. Alternatively, the network coverage time ratio information may further indicate the ratio of the time period covered by the network of the candidate device to the time of interest in the form of a decimal, a fraction, a percentage, etc. Specifically, it may be determined according to the demand of actual use, and the embodiment of the present application is not limited thereto.

[0041] In an embodiment of the present application, the network signal quality information is for indicating a network signal quality of the device, where the network signal quality may include at least one of signal quality, signal strength, and signal stability.

[0042] The network signal quality may be indicated by an average or peak value of a network signal quality parameter.

[0043] In an embodiment of the present application, if the wireless access method is WLAN, the network signal quality may be indicated by at least one parameter of a received signal strength indication (RSSI) and a round trip time (RTT).

[0044] Optionally, in an embodiment of the present application, the first request message may include report granularity indication information. The report granularity indication information may be for instructing a candidate device to report network performance analysis information corresponding to the candidate device with device granularity. For example, the report granularity indication information instructs a candidate device to report network performance analysis information corresponding to the candidate UE with per UE granularity. In this way, the first communication device can select an appropriate UE to participate in the federated learning by determining the network performance of each UE among the M candidate UEs.

[0045] Optionally, in the embodiment of the present application, the first request information may include filtering information, where the filtering information may include at least one of the following:

[0046] a) Area of ​​interest, which may be referred to as an area of ​​interest, for example one or more cells, or one or more tracking areas (TAs).

[0047] b) Radio access method limitation information, the radio access method limitation information may be for indicating the radio access method of the candidate device, for the description of the radio access method, see the relevant description of the above embodiment.

[0048] c) Interest time. The interest time may be a time when the first communication device is scheduled to perform federated learning. For example, the interest time may be 00:00-04:00 on March 15, 2020, and may be determined according to actual usage demand.

[0049] Optionally, in an embodiment of the present application, the above filtering information may further include at least one of the following:

[0050] d) The number of candidate devices that need to be replied by the second communication device, i.e. the value of M, for example M=500.

[0051] e) network signal quality limitation information of the candidate device, the network signal quality limitation information may be for indicating a network signal quality threshold of the required candidate device, the network signal quality threshold may be a minimum requirement for the network signal quality of the candidate device.

[0052] As an illustrative example, taking signal stability (which may be expressed as the percentage of time that network signal strength remains above a target value) as an example, a network signal stability threshold of 90% indicates that the signal strength is required to reach the target value for 90% or more of the time during the time of interest of the candidate device.

[0053] f) Algorithm Qualification Information. The algorithm qualification information may be for indicating algorithms for machine learning or other artificial intelligence (AI) data analysis tasks that the required candidate devices support, e.g., deep learning, linear regression, etc.

[0054] g) Model training accuracy limit information. The model training accuracy limit information may be for indicating the training accuracy that the available model can achieve when the requested candidate device participates in the federated learning, i.e., the model accuracy that the available model can achieve after the training is completed. That is, the ratio of the number of correct predictions (judgments) made by the model after the training is completed to the total number of predictions, for example, the accuracy rate is 90%.

[0055] h) Model training speed limit information. The model training speed limit information may be for indicating the training time required to train the model available when the requested candidate device participates in the federated learning to a first training accuracy (e.g., 80% accuracy). Specifically, it may be the training time required for the model to achieve the first training accuracy when the candidate device locally trains the model. The longer the required training time, the slower the training speed, and the shorter the required training time, the faster the training speed.

[0056] i) Associated learning memory space limit information. The memory space limit information is for indicating the amount of memory space that a requested candidate device reserves for information such as models and data for associative learning, e.g., 10 megabits (MB).

[0057] Optionally, in an embodiment of the present application, the first request message may further include an analytic identifier (analytic ID) of network performance, and the analytic identifier may be for indicating a task corresponding to the first request message, such as, for example, the current task is to obtain network performance of a candidate device that meets a request for filtering information. Exemplarily, the network performance analytic identifier may be WLAN performance or NR performance.

[0058] Optionally, in an embodiment of the present application, the first request message may further include reporting limitation information. The reporting limitation information may include at least one of the following:

[0059] A) Sorting information of the candidate devices. The sorting information is for instructing the second communication device to output the candidate devices in ascending or descending order of a certain parameter / scale. If the signal strength is output in descending order, when the second communication device returns the result (i.e., transmits the network performance analysis information to the first communication device), the candidate devices may be arranged in ascending order of signal strength.

[0060] B) Grouping information of candidate devices. The grouping information is for instructing the second communication device to group the candidate devices by a certain parameter / factor (e.g., time, location, etc.). For example, the second communication device may group, among all the candidate devices, the candidate devices that perform federated learning from 10:00 to 12:00 noon into one group.

[0061] C) The percentage of the time period covered by the network of the candidate device during the time of interest relative to the time of interest (i.e., the percentage of time covered by the network). For the description of the proportion of time covered by the network, reference can be made to the relevant description in the above embodiment, which will not be repeated here to avoid duplication.

[0062] D) Format of network performance analysis information.

[0063] E) Contents included in network performance analysis information.

[0064] In the device determination method provided in the embodiments of the present application, the wireless access method information of the device, the time information available for participating in federated learning, location information, time period information covered by the network, ratio information of the time period covered by the network to the time of interest, and network signal quality information can all reflect the network performance corresponding to the device, so that when the first communication device receives the network performance analysis information, it can determine the network performance corresponding to each candidate device among the M candidate devices, so that the first communication device can determine the candidate devices that meet the network performance requirements of federated learning as devices to participate in federated learning, that is, the first communication device can select appropriate devices to participate in federated learning.

[0065] Optionally, before the above step 203, the device determination method provided in the embodiment of the present application may further include step 205 and step 206 described below.

[0066] In step 205, the first communication device determines N devices to participate in the federated learning from the M candidate devices based on the network performance analysis information, where N is a positive integer less than or equal to M.

[0067] In step 206, the first communication device establishes connections with the N devices and performs federated learning.

[0068] In an embodiment of the present application, after receiving the network performance analysis information, the first communication device may determine N devices to participate in federated learning from the M candidate devices, and then establish connections with the N devices to perform federated learning, thereby obtaining a federated learning model that meets the needs of the first communication device.

[0069] For example, if the first communication device limits the UEs that need to connect to the WLAN and whose signal strength needs to reach a threshold in the filtering information, and limits federated learning to be performed within the range of A City on March 15, 2020, the M candidate UEs are UEs that meet these conditions. The first communication device may select according to the number of UEs that overlap on March 15, 2020. For example, if there are 500 UEs that meet the conditions and can participate in federated learning between 2:00 p.m. and 3:00 p.m. on March 15, 2020, and the number of UEs that overlap on that day is the largest between 2:00 p.m. and 3:00 p.m., the first communication device may select the 500 UEs as devices that will participate in federated learning. As a result, the first communication device can establish a connection with the 500 UEs between 2:00 p.m. and 3:00 p.m. on March 15, 2020, and perform federated learning. Alternatively, the first communication device may select a UE with the best network signal strength as a device that will participate in federated learning.

[0070] Optionally, in an embodiment of the present application, before the above step 205, the device determination method provided in the embodiment of the present application may further include at least one of step 207 and step 208 described below.

[0071] In addition, the present application does not limit the specific order / timing of execution of step 207 and step 208, and step 207 and step 208 may be executed before step 201 or after step 204. Specifically, it may be determined according to the needs of actual use, and the embodiments of the present application are not limited thereto.

[0072] For step 207, the first communication device determines that the M candidate devices are willing to engage in federated learning.

[0073] For step 208, the first communication device determines that the M candidate devices are capable of federated learning.

[0074] In an embodiment of the present application, before determining N devices from the M candidate devices to participate in federated learning, the first communication device may determine in advance whether the M candidate devices are willing and / or capable of federated learning based on network performance analysis information, and if it is determined that the M candidate devices are willing and / or capable of federated learning, it can determine the N devices from the M candidate devices to participate in federated learning.

[0075] Optionally, in the embodiment of the present application, the above step 207 may be realized by the following steps 207a and 207b.

[0076] In step 207a, the first communication device obtains federated learning willingness information of the M candidate devices from the third communication device.

[0077] In step 207b, the first communication device determines that the M candidate devices are willing to engage in federated learning based on the willingness information of the M candidate devices to engage in federated learning.

[0078] In an embodiment of the present application, after the first communication device obtains the willingness information of the M candidate devices to engage in federated learning from the third communication device, the first communication device can determine that the M candidate devices are willing to engage in federated learning based on the willingness information of the M candidate devices to engage in federated learning.

[0079] Optionally, in an embodiment of the present application, the first communication device obtains federated learning willingness information of Q devices from a third communication device, and selects federated learning willingness information of the M candidate devices from the federated learning willingness information of the Q devices. Here, the Q devices may include the M candidate devices.

[0080] In an embodiment of the present application, the third communication device may be a UDM.

[0081] Optionally, in an embodiment of the present application, the motivation information of the associative learning is: Indication of willingness to participate in associative learning; and and condition information for participating in federated learning.

[0082] Optionally, in an embodiment of the present application, the condition information for participating in the federated learning may include at least one of the following:

[0083] The wireless access method used when participating in federated learning, for example, non-3GPP (registered trademark) WLAN.

[0084] The time to participate in federated learning. That is, the time when you can participate in federated learning, for example, 2:00-5:00 AM.

[0085] The location when participating in federated learning. For example, the area in which the node is located or the cell accessed when participating in federated learning.

[0086] Alternatively, in the embodiment of the present application, the above step 208 may be realized by steps 208a and 208b described below.

[0087] In step 208a, the first communication device obtains federated learning capability information of the M candidate devices from the third communication device.

[0088] In step 208b, the first communication device determines, based on the federated learning capability information of the M candidate devices, that the M candidate devices are capable of federated learning.

[0089] In an embodiment of the present application, after the first communication device obtains the federated learning capability information of the M candidate devices from the third communication device, the first communication device can determine that the M candidate devices are capable of federated learning based on the federated learning capability information of the M candidate devices.

[0090] Optionally, in an embodiment of the present application, the first communication device obtains federated learning willingness information of S devices from a third communication device, and selects federated learning willingness information of the M candidate devices from the federated learning willingness information of the S devices. Here, the S devices may include the M candidate devices.

[0091] Optionally, in an embodiment of the present application, the above-mentioned associative learning capability information may include at least one of the following:

[0092] Models that can be used to participate in federated learning, e.g. models using specific network architectures such as Residual Networks (ResNet), Inception-v3, etc.

[0093] Algorithms that can be used when participating in federated learning, such as gradient descent.

[0094] The training accuracy of a model that can be achieved when participating in federated learning. That is, the model accuracy that the available model can achieve after training is completed, for example, the highest accuracy that can be achieved. That is, the proportion of the number of correct predictions and judgments to the total number of numbers after training is completed, for example, the accuracy rate is 90%.

[0095] A training speed of a model achievable when participating in federated learning, the training speed being intended to indicate the training time required to train an available model to a first training accuracy when participating in federated learning, i.e., the training time (e.g., 30 minutes) required to train the model to a first training accuracy (e.g., 80%) when a first device locally trains the available model, where the longer the training time, the slower the training speed, and the shorter the training time, the faster the training speed.

[0096] The size of the memory space participating in the federated learning. In other words, the size of the memory space reserved for information such as the federated learning model and data, for example 15MB.

[0097] Optionally, before the above step 207a or step 208a, the device determination method provided in the embodiment of the present application may further include step 209 described below.

[0098] In step 209, the first communication device acquires network capability public information of the third communication device from the fifth communication device.

[0099] The fifth communication device may be an NEF or other communication device, and can be specifically determined according to the needs of actual use.

[0100] The first communication device may exchange information with the third communication device by transmitting second request information for requesting acquisition of public information of the network function of the third communication device to the fifth communication device. For example, the first communication device may acquire federated learning willingness information of the M candidate devices and / or federated learning capability information of the M candidate devices from the third communication device.

[0101] Optionally, in an embodiment of the present application, before the above step 203, the device determination method provided in the embodiment of the present application may further include step 210 and step 211 described below.

[0102] In step 210, the second communication device obtains network performance data corresponding to the M candidate devices from the fourth communication device.

[0103] In step 211, the second communication device analyzes network performance data corresponding to the M candidate devices to obtain network performance analysis information corresponding to the M candidate devices.

[0104] In an embodiment of the present application, the second communication device obtains network performance data corresponding to the M candidate devices from the fourth communication device, and then analyzes the network performance data corresponding to the M candidate devices to obtain network performance analysis information corresponding to the M candidate devices.

[0105] Optionally, in the embodiment of the present application, the fourth communication device may include at least one of network elements such as SMF, OAM, UDM and DC-AF.

[0106] Optionally, in the embodiment of the present application, the above step 210 may be realized by at least one of steps 210a and 210b described below.

[0107] In step 210a, the second communication device obtains at least one of radio access method information, time information covered by the network, and time information in the network of the session corresponding to the M candidate devices from the SMF.

[0108] In step 210b, the second communication device obtains at least one of network identifier information, network signal quality information corresponding to the M candidate devices from a network management device.

[0109] Exemplarily, taking the case where the second communication device is an NWDAF as an example, the NWDAF may obtain network signal quality information corresponding to the M candidate devices, for example, signal quality information (for example, RTT, RSSI, etc.) of the device connecting to the WLAN from the OAM, and may obtain network identifier information corresponding to the M candidate devices, for example, Service Set Identifier (SSID), etc. from the OAM. In addition, the NWDAF may obtain radio access method information corresponding to the M candidate devices, for example, WLAN, 5G NR, 4G EUTRAN, etc. from the SMF, and may obtain time information covered by the network corresponding to the M candidate devices, for example, time covered by WLAN, from the SMF. In addition, the NWDAF may obtain algorithm information supported by the M candidate devices, achievable model training accuracy information, etc. from the UDM or DCAF. In addition, the NWDAF may obtain flow rate information corresponding to the M candidate devices from the UPF.

[0110] In an embodiment of the present application, when the second communication device obtains network performance data corresponding to the M candidate devices, it can analyze the network performance data of the M candidate devices to obtain network performance analysis results for the M candidate devices, and further generate network performance analysis information corresponding to the M candidate devices based on the network performance analysis results of the M candidate devices.

[0111] Hereinafter, with reference to Table 1, the network performance analysis result of the device will be illustratively described by taking the case where the wireless access method of the device is WLAN as an example.

[0112] [Table 1]

[0113] Optionally, in an embodiment of the present application, before the above step 203, the device determination method provided in the embodiment of the present application may further include step 212 described below.

[0114] In step 212, the second communication device determines M candidate devices based on the filtering information included in the first request message.

[0115] Each candidate device among the M candidate devices: Located within a region of interest; The radio access method is a radio access method designated by the radio access method limitation information; and being covered by the network during the time of interest.

[0116] Optionally, in an embodiment of the present application, each candidate device among the M candidate devices comprises: the network signal quality is equal to or greater than the network signal quality indicated by the network signal quality limit information; The supported algorithms are those indicated by the algorithm limitation information; and The training accuracy of the model that can be achieved when participating in federated learning is equal to or greater than the training accuracy indicated by the training accuracy limit information of the model; The training speed of the model that can be achieved when participating in the associative learning is equal to or greater than the training speed indicated by the training speed limit information of the model; At least one condition may further be satisfied: the size of the memory space participating in the associative learning is equal to or larger than the size of the memory space indicated by the memory space limiting information for the associative learning.

[0117] For example, if the training accuracy indicated by the training accuracy limitation information of the model is 85%, and the training accuracy of the model that a device among the K devices can achieve during federated learning is 93%, the device may be determined as a candidate device.

[0118] Optionally, in an embodiment of the present application, before the above step 203, the device determination method provided in the embodiment of the present application may further include step 213 and / or step 214 described below.

[0119] In step 213, the second communication device determines that the M candidate devices are willing to engage in federated learning.

[0120] In step 214, the second communication device determines that the M candidate devices are capable of federated learning.

[0121] In an embodiment of the present application, before the second communication device transmits network performance analysis information to the first communication device, the first communication device may determine in advance whether the M candidate devices are willing and / or capable of federated learning. If it is determined that the M candidate devices are willing and / or capable of federated learning, the second communication device may transmit network performance analysis information corresponding to the M candidate devices to the first communication device.

[0122] Alternatively, in the embodiment of the present application, the above step 213 may be realized by steps 213a and 213b described below.

[0123] In step 213a, the second communication device obtains federated learning willingness information of the M candidate devices from the third communication device.

[0124] In step 213b, the second communication device determines that the M candidate devices are willing to engage in federated learning based on the federated learning willingness information of the M candidate devices.

[0125] In an embodiment of the present application, when the second communication device obtains the federated learning willingness information of the M candidate devices from the third communication device, the first communication device may determine that the M candidate devices are willing to federate learning based on the federated learning willingness information of the M candidate devices, so as to send network performance analysis information corresponding to the M candidate devices willing to feed learning to the first communication device. In this way, the first communication device can directly select devices to participate in federated learning from the M candidate devices.

[0126] Optionally, in an embodiment of the present application, the second communication device obtains the federated learning willingness information of the W devices from the third communication device, and selects the federated learning willingness information of the M candidate devices from the federated learning willingness information of the W devices. Note that the W devices may include the M candidate devices.

[0127] In an embodiment of the present application, the third communication device may be a UDM.

[0128] For the explanation of the motivation information for associative learning, please refer to the relevant explanation in the above embodiment, and in order to avoid duplication, it will not be repeated here.

[0129] Alternatively, in the embodiment of the present application, the above step 214 may be realized by steps 214a and 214b described below.

[0130] In step 214a, the second communication device obtains federated learning capability information of the M candidate devices from the third communication device.

[0131] In step 214b, the second communication device determines, based on the federated learning capability information of the M candidate devices, that the M candidate devices are capable of federated learning.

[0132] In an embodiment of the present application, when the second communication device obtains the federated learning capability information of the M candidate devices from the third communication device, the first communication device may determine that the M candidate devices are capable of federated learning based on the federated learning capability information of the M candidate devices, so as to send network performance analysis information corresponding to the M candidate devices capable of federated learning to the first communication device. In this way, the first communication device can directly select devices to participate in federated learning from the M candidate devices.

[0133] Optionally, in an embodiment of the present application, the second communication device obtains federated learning capability information of P devices from a third communication device, and selects federated learning capability information of the M candidate devices from the federated learning willingness information of the P devices. Here, the P devices may include the M candidate devices.

[0134] For the explanation of the ability information of associative learning, please refer to the relevant explanation in the above embodiment, and in order to avoid duplication, it will not be described again here.

[0135] Optionally, before the above step 213a or step 214a, the device determination method provided in the embodiment of the present application may further include step 215 described below.

[0136] In step 215, the second communication device acquires network capability public information of the third communication device from the fifth communication device.

[0137] The fifth communication device may be an NEF or other communication device, and can be specifically determined according to the needs of actual use.

[0138] The second communication device may exchange information with the third communication device by transmitting second request information for requesting acquisition of public information of the network function of the third communication device to the fifth communication device. For example, the second communication device may acquire federated learning willingness information of the M candidate devices and / or federated learning capability information of the M candidate devices from the third communication device.

[0139] Hereinafter, and with reference to FIG. 2 and FIG. 3, a device determination method provided in an embodiment of the present application will be illustratively described.

[0140] As shown in FIG. 2, in step 0a, a consumer service entity such as an AF obtains network capability disclosure information about a communication device such as a UDM / NRF / DCAF by sending a request to a NEF to later obtain federated learning willingness information and / or federated learning capability information of a candidate device from a communication device such as a UDM, and determine whether the device has federated learning capability and / or willingness.

[0141] In step 0b, a consumer service entity such as an AF requests a capability memory network element such as a UDM / NRF / DC-AF to obtain federated learning willingness information and / or federated learning capability information.

[0142] As shown in FIG. 3, in step 1, a consumer service entity such as an AF sends a first request message (which can be Nnwdaf_AnalyticsInfo or Nnwdaf_AnalyticsSubscription) to the NWDAF to request obtaining network performance analysis information.

[0143] In step 2, the NWDAF obtains network performance data, such as radio access method, signal quality, etc., for the UE, from a data provider, such as an SMF, an OAM, an UDM, etc., according to the task description and the constraints of the first request message. Step 2 may include steps 2a, 2b, and 2c.

[0144] In step 3, the NWDAF uses and analyzes the acquired network performance data to obtain a network performance analysis result at UE granularity, thereby obtaining network performance analysis information.

[0145] In step 4, the NWDAF returns a task response message based on the description information of the first request message in step 1, i.e., sends network performance analysis information to a consumer service entity such as an AF. The NWDAF may respond based on the Nnwdaf_AnalyticsInfo or Nnwdaf_AnalyticsSubscription used in step 1.

[0146] In step 5, a consumer service entity such as an AF determines the UE(s) that will participate in the federated learning based on the response message returned in step 4.

[0147] In step 6, a consumer service entity such as an AF establishes a connection with the UE(s) participating in the federated learning based on the identifier information of the UE(s) determined in step 5, and performs federated learning.

[0148] In addition, the device determination method provided in the embodiment of the present application may be executed by a device determination device. In the embodiment of the present application, the device determination device provided in the embodiment of the present application will be described by taking the case where the device determination device executes the device determination method as an example.

[0149] As shown in Fig. 4, an embodiment of the present application provides a device determination apparatus 300, including a sending module 301 and a receiving module 302. The sending module 301 is for sending a first request message to a second communication device to request to obtain network performance analysis information, and the receiving module 302 is for receiving network performance analysis information from the second communication device, where the network performance analysis information includes network performance analysis information corresponding to M candidate devices, where M is a positive integer. The network performance analysis information corresponding to one candidate device includes at least one of the following information: wireless access method information of one candidate device, time information of one candidate device that can participate in federated learning, location information of one candidate device, time period information covered by the network of one candidate device, ratio information of the time period covered by the network of one candidate device within the time period of interest to the time period of interest, and network signal quality information of one candidate device.

[0150] Optionally, the device determination apparatus further includes a determination module and an execution module, where the determination module is for determining N devices to participate in the federated learning from the M candidate devices based on the network performance analysis information, where N is a positive integer equal to or less than M, and the execution module is for establishing connections with the N devices and performing federated learning.

[0151] Optionally, the first request message includes reporting granularity indication information for instructing the device to report network performance corresponding to the candidate device as a granularity.

[0152] Optionally, the first request message comprises: A region of interest; Radio access method limited information; and a time of interest.

[0153] Optionally, the determination module is further for determining that the M candidate devices are willing to engage in federated learning, and / or the determination module is further for determining that the M candidate devices are capable of federated learning.

[0154] Optionally, the determination module includes an acquisition sub-module for acquiring associative learning willingness information of the M candidate devices from the third communication device, and a determination sub-module for determining that the M candidate devices are willing to engage in associative learning based on the associative learning willingness information of the M candidate devices.

[0155] Optionally, the determination module includes an acquisition sub-module for acquiring federated learning capability information of the M candidate devices from the third communication device, and a determination sub-module for determining that the M candidate devices are capable of federated learning based on the federated learning capability information of the M candidate devices.

[0156] Optionally, motivation information for associative learning is Indication of willingness to participate in associative learning; and and condition information for participating in federated learning.

[0157] Optionally, the condition information for participating in the federated learning is Wireless access method when participating in federated learning; Time to participate in federated learning, and at least one of the position when participating in federated learning.

[0158] Optionally, the ability information of associative learning is Models that can be used when participating in federated learning and Algorithms available for participating in federated learning, The achievable training accuracy of models when participating in federated learning, a training rate for indicating the training time required to train the available models to a first training accuracy achievable when participating in federated learning; and the size of the memory space participating in the associative learning.

[0159] Optionally, the second communication device includes an NWDAF.

[0160] An embodiment of the present application provides a device determination device, in which the wireless access method information of a device, the time information available for participating in federated learning, location information, time period information covered by the network, ratio information of the time period covered by the network to the time of interest, and network signal quality information can all reflect the network performance corresponding to a device. Therefore, upon receiving network performance analysis information, the device determination device can determine the network performance corresponding to each candidate device among the M candidate devices, and thereby determine the candidate devices that meet the network performance requirements of federated learning as devices to participate in federated learning, that is, the device determination device can select appropriate devices to participate in federated learning.

[0161] As shown in Fig. 5, an embodiment of the present application provides a device determination apparatus 400, including a receiving unit 401 and a sending unit 402. The receiving unit 401 may be for receiving a first request message for requesting to obtain network performance analysis information from a first communication device. The sending unit is for sending the network performance analysis information to the first communication device, where the network performance analysis information includes network performance analysis information corresponding to M candidate devices, where M is a positive integer. The network performance analysis information corresponding to one candidate device includes at least one kind of information: radio access method information of the one candidate device, time information of the one candidate device that can participate in federated learning, location information of the one candidate device, time period information covered by the network of the one candidate device, ratio information of the time period covered by the network of the one candidate device within the time period of interest to the time period of interest, and network signal quality information of the one candidate device.

[0162] Optionally, the first request message includes reporting granularity indication information for instructing the device to report network performance corresponding to the candidate device as a granularity.

[0163] Optionally, the first request message comprises: A region of interest; Radio access method limited information; and a time of interest.

[0164] Optionally, the device determination apparatus further includes an acquisition unit for acquiring network performance data corresponding to the M candidate devices from the fourth communication device, and an analysis unit for analyzing the network performance data corresponding to the M candidate devices and obtaining network performance analysis information corresponding to the M candidate devices.

[0165] Optionally, the acquiring unit includes a first acquiring subunit for acquiring at least one of radio access method information corresponding to the M candidate devices, time information covered by the network, and time information in the network of the session from a session management function network element SMF, and a second acquiring subunit for acquiring at least one of network identifier information corresponding to the M candidate devices, and network signal quality information from a network management device.

[0166] Optionally, the device determination apparatus further includes a determination unit for determining the M candidate devices based on filtering information included in the first request message, and each candidate device among the M candidate devices includes: Located within a region of interest; The wireless access method is a wireless access method that is a wireless access method indicated by the wireless access method limitation information; and being covered by the network during the time of interest.

[0167] Optionally, the device determination apparatus further includes a determining unit for determining that the M candidate devices are willing to perform federated learning, and / or a determining unit for determining that the M candidate devices are capable of federated learning.

[0168] Optionally, the determination unit includes an acquisition subunit for acquiring associative learning willingness information of the M candidate devices from the third communication device, and a determination subunit for determining that the M candidate devices are willing to engage in associative learning based on the associative learning willingness information of the M candidate devices.

[0169] Optionally, the determination unit includes an acquisition subunit for acquiring federated learning capability information of the M candidate devices from the third communication device, and a determination subunit for determining that the M candidate devices are capable of federated learning based on the federated learning capability information of the M candidate devices.

[0170] Optionally, motivation information for associative learning is Indication of willingness to participate in associative learning; and and condition information for participating in federated learning.

[0171] Optionally, the condition information for participating in the federated learning is Wireless access method when participating in federated learning; Time to participate in federated learning, and at least one of the position when participating in federated learning.

[0172] Optionally, the ability information of associative learning is Models that can be used when participating in federated learning and Algorithms available for participating in federated learning, The achievable training accuracy of models when participating in federated learning, a training rate for indicating the training time required to train the available models to a first training accuracy achievable when participating in federated learning; and the size of the memory space participating in the associative learning.

[0173] An embodiment of the present application provides a device determination device, in which the wireless access method information of a device, the time information available for participating in federated learning, location information, time period information covered by the network, ratio information of the time period covered by the network to the time of interest, and network signal quality information can all reflect the network performance corresponding to a device. After the device determination device sends network performance analysis information to the first communication device, the first communication device can determine the network performance corresponding to each candidate device among the M candidate devices, so that the first communication device can determine the candidate devices that meet the network performance requirements of federated learning as devices to participate in federated learning, i.e., select appropriate devices to participate in federated learning.

[0174] The device determination apparatus in the embodiment of the present application may be an electronic device, for example, an electronic device having an operating system, or may be a component in an electronic device, for example, an integrated circuit or a chip. The electronic device may be a terminal or other devices other than a terminal. Exemplarily, the terminal may include, but is not limited to, the types of terminal 11 listed above, and the other devices may be servers, network attached storage (NAS), etc., and the embodiment of the present application does not make any specific limitations.

[0175] The device determination apparatus provided in the embodiments of the present application can realize each procedure implemented by the above method embodiments, and achieves similar technical effects, so they will not be repeated here to avoid duplication.

[0176] Optionally, as shown in FIG. 6 , an embodiment of the present application further provides a communication device 500, including a processor 501 and a memory 502, in which a program or command executable by the processor 501 is stored, for example, when the communication device 500 is a first communication device, the program or command can be executed by the processor 501 to realize each step of the embodiment of the device determination method and achieve similar technical effects, and when the communication device 500 is a second communication device, the program or command can be executed by the processor 501 to realize each step of the embodiment of the device determination method and achieve similar technical effects, which will not be repeated here to avoid duplication.

[0177] An embodiment of the present application further provides a communication device, including a processor and a communication interface, where when the communication device is a first communication device, the communication interface is for sending a first request message to a second communication device and receiving network performance analysis information from the second communication device, and when the communication device is a second communication device, the communication interface is for receiving the first request message from the first communication device and sending network performance analysis information to the first communication device, the network performance analysis information includes network performance analysis information corresponding to M candidate devices, M is a positive integer, and the network performance analysis information corresponding to one candidate device includes at least one of the following information: radio access method information of one candidate device, time information of one candidate device that can participate in federated learning, location information of one candidate device, time period information covered by the network of one candidate device, ratio information of the time period covered by the network of one candidate device within a time period of interest to the time period of interest, and network signal quality information of one candidate device. The embodiments of the communication device correspond to the method embodiments of the first communication device or the second communication device, and each implementation process and realization means of the method embodiments are all applicable to the embodiments of the communication device, and can achieve similar technical effects.

[0178] Specifically, an embodiment of the present application further provides a communication device. As shown in Fig. 7, the communication device 600 includes a processor 601, a network interface 602, and a memory 603, where the network interface 602 is, for example, a common public radio interface (CPRI).

[0179] The communication device 600 of the embodiment of the present invention further includes a command or program stored in the memory 603 and executable by the processor y01. The processor 601 can call the command or program in the memory y03 to execute the method executed by each module in the device determination apparatus, and achieve similar technical effects, so that they will not be repeated here to avoid duplication.

[0180] The embodiments of the present application further provide a readable storage medium, which stores a program or command, and when the program or command is executed by a processor, can realize each procedure of the above-mentioned device determination method embodiment and achieve the same technical effect, so that they will not be described again here to avoid duplication.

[0181] The processor is the processor in the terminal described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read only memory ROM, a random access memory RAM, a magnetic disk, an optical disk, and the like.

[0182] The embodiment of the present application further provides a chip, which includes a processor and a communication interface coupled thereto, and the processor executes a program or command to realize each procedure of the embodiment of the device determination method described above, and achieves similar technical effects, so that the description will not be repeated here to avoid duplication.

[0183] The chip described in the embodiments of the present application is also called a system on chip, a system chip, a chip system, or an SoC.

[0184] The embodiments of the present application further provide a computer program / program product, which is stored in a storage medium and executed by at least one processor to realize each procedure of the above-mentioned device determination method embodiments and achieve similar technical effects, so that they will not be described again here to avoid duplication.

[0185] It should be noted that in this specification, the terms "comprise", "consist of" or any other variants are intended to include a non-exclusive inclusion, whereby a process, method, article or apparatus that includes a set of elements includes not only those elements, but also other elements not expressly stated or inherent to such process, method, article or apparatus. Unless otherwise specified, an element limited by the phrase "comprises a" does not exclude the presence of other identical elements in the process, method, article or apparatus that includes the element. In addition, the scope of the method and apparatus in the embodiments of this application is not limited to performing functions in the order shown or discussed herein, and may further include performing functions substantially simultaneously or in the opposite order, depending on the functions involved. For example, the above methods may be performed in a different order than described, and further, individual steps may be added, omitted, or combined. Also, features described with reference to some examples may be combined with other examples.

[0186] From the above description of the embodiments, it can be clearly understood by those skilled in the art that the methods of the above embodiments can be realized in the form of a combination of software and a necessary common hardware platform. Of course, it can also be realized by hardware, but in many cases the former is a more preferred embodiment. Based on this view, the technical means of the present application can be substantially or partly contributed to the prior art can be implemented as a software product, and the computer software product is stored in a storage medium (e.g., ROM / RAM, magnetic disk, optical disk) and includes a plurality of commands for causing a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods of the embodiments of the present application.

[0187] Although the examples of the present application have been described above with reference to the drawings, the present application is not limited to the above specific embodiments, which are merely illustrative and not limiting. Based on the suggestions of this application, many forms that a person skilled in the art can obtain without departing from the spirit of the present application and the scope of protection of the claims are all within the scope of protection of the present application.

[0188] (CROSS REFERENCE TO RELATED APPLICATIONS) This application claims priority to a Chinese patent application filed with the China Intellectual Property Office on March 28, 2022, bearing application number 202210314847.1 and entitled "Device determination method, apparatus and communication device", the entire contents of which are incorporated herein by reference.

Claims

1. A first communication device sending a first request message to a second communication device to request obtaining network performance analysis information; The first communication device receives the network performance analysis information from the second communication device, the network performance analysis information including network performance analysis information corresponding to M candidate devices, where M is a positive integer; The network performance analysis information corresponding to one candidate device is Radio access method information of the one candidate device; Time information of the one candidate device available for participating in federated learning; Location information of the one candidate device; time period information covered by the network of said one candidate device; A ratio of a time period covered by the network of the one candidate device during a time period of interest to the time period of interest; and network signal quality information of the one candidate device.

2. After the step of the first communication device receiving the network performance analysis information from the second communication device, the method further comprises: The first communication device determines N devices to participate in the federated learning from the M candidate devices based on the network performance analysis information, where N is a positive integer equal to or less than M; The method of claim 1 , further comprising: the first communication device establishing a connection with the N devices and performing federated learning.

3. The method of claim 1 , wherein the first request message includes report granularity instruction information for instructing the candidate device to report network performance analysis information corresponding to the candidate device with device granularity.

4. The first request message includes: A region of interest; Radio access method limited information; The method of claim 1 , further comprising filtering information including at least one of:

5. Before the step of the first communication device determining N devices to participate in the federated learning from the M candidate devices based on the network performance analysis information, the method further comprises: The first communication device determines that the M candidate devices are willing to engage in federated learning; and / or The method of claim 2 , further comprising the first communication device determining that the M candidate devices are capable of federated learning.

6. The step of the first communication device determining that the M candidate devices are willing to engage in federated learning includes: The first communication device acquires federated learning willingness information of the M candidate devices from a third communication device; The method of claim 5 , comprising: the first communication device determining that the M candidate devices are willing to engage in federated learning based on willingness information of the M candidate devices to engage in federated learning.

7. The step of the first communication device determining that the M candidate devices are capable of federated learning includes: The first communication device acquires federated learning capability information of the M candidate devices from a third communication device; The method of claim 5 , comprising: the first communication device determining, based on federated learning capability information of the M candidate devices, that the M candidate devices are capable of federated learning.

8. The motivation information for the associative learning is Indication of willingness to participate in associative learning; and and condition information for participating in federated learning.

9. The condition information for participating in the federated learning is Wireless access method when participating in federated learning; Time to participate in federated learning, and a location when participating in federated learning.

10. The associative learning ability information is Models that can be used when participating in federated learning and Algorithms available for participating in federated learning, The achievable training accuracy of models when participating in federated learning, a training speed of the models achievable when participating in associative learning, the training speed being for indicating a training time required to train the available models to a first training accuracy; and and a size of the memory space participating in the federated learning.

11. The method of claim 1 , wherein the first communication device includes an application function AF and the second communication device includes a network data analysis function NWDAF.

12. receiving, by the second communication device, a first request message from the first communication device for requesting to obtain network performance analysis information; The second communication device transmits the network performance analysis information to the first communication device, the network performance analysis information including network performance analysis information corresponding to M candidate devices, where M is a positive integer; The network performance analysis information corresponding to one candidate device is Radio access method information of the one candidate device; Time information of the one candidate device available for participating in federated learning; Location information of the one candidate device; time period information covered by the network of said one candidate device; A ratio of a time period covered by the network of the one candidate device during a time period of interest to the time period of interest; and network signal quality information of the one candidate device.

13. The method of claim 12 , wherein the first request message includes reporting granularity indication information for instructing the candidate device to report network performance analysis information corresponding to the candidate device with device granularity.

14. The first request message includes: A region of interest; Radio access method limited information; The method of claim 12 , further comprising filtering information including at least one of:

15. Prior to the step of the second communication device transmitting the network performance analysis information to the first communication device, the method further comprises: obtaining, by the second communication device, network performance data corresponding to the M candidate devices from a fourth communication device; The method of claim 12 , further comprising: the second communication device analyzing network performance data corresponding to the M candidate devices to obtain network performance analysis information corresponding to the M candidate devices.

16. The step of the second communication device obtaining network performance data corresponding to the M candidate devices from a fourth communication device, The second communication device obtains at least one of radio access method information corresponding to the M candidate devices from a session management function network element SMF, time information covered by a network, and time information in the network of a session; and c) the second communications device obtaining at least one of network identifier information, network signal quality information corresponding to the M candidate devices from a network management device.

17. Before the second communication device transmits the network performance analysis information to the first communication device, the method further comprises: The method further includes the step of: the second communication device determining the M candidate devices based on filtering information included in the first request message, and each candidate device among the M candidate devices: Located within the region of interest; The radio access method is a radio access method indicated by the radio access method limitation information; 15. The method according to claim 12, wherein the method satisfies at least one of the following conditions: being covered by a network during the time of interest.

18. Prior to the step of the second communication device transmitting the network performance analysis information to the first communication device, the method further comprises: the second communication device determining that the M candidate devices are willing to engage in federated learning; and / or The method of claim 12 , further comprising the step of the second communication device determining that the M candidate devices are capable of federated learning.

19. The step of the second communication device determining that the M candidate devices are willing to engage in federated learning includes: The second communication device acquires federated learning willingness information of the M candidate devices from a third communication device; The method of claim 18 , comprising: the second communication device determining that the M candidate devices are willing to engage in federated learning based on willingness information of the M candidate devices to engage in federated learning.

20. The step of the first communication device determining that the M candidate devices are capable of federated learning includes: The second communication device acquires federated learning capability information of the M candidate devices from a third communication device; The method of claim 18 , comprising: the second communication device determining, based on federated learning capability information of the M candidate devices, that the M candidate devices are capable of federated learning.

21. The motivation information for the associative learning is Indication of willingness to participate in associative learning; and and condition information for participating in federated learning.

22. The condition information for participating in the federated learning is Wireless access method when participating in federated learning; Time to participate in federated learning, and a location when participating in federated learning.

23. The associative learning ability information is Models that can be used when participating in federated learning and Algorithms available for participating in federated learning, The achievable training accuracy of models when participating in federated learning, a training speed of the models achievable when participating in associative learning, the training speed being for indicating a training time required to train the available models to a first training accuracy; and and a size of the memory space participating in the federated learning.

24. 13. The method of claim 12, characterized in that the first communication device includes an application function AF and the second communication device includes a network data analysis function NWDAF.

25. a sending module for sending a first request message to a second communication device to request obtaining network performance analysis information; a receiving module for receiving the network performance analysis information from the second communication device, the network performance analysis information including network performance analysis information corresponding to M candidate devices, where M is a positive integer; The network performance analysis information corresponding to one candidate device is Radio access method information of the one candidate device; Time information of the one candidate device available for participating in federated learning; Location information of the one candidate device; time period information covered by the network of said one candidate device; A ratio of a time period covered by the network of the one candidate device during a time period of interest to the time period of interest; and network signal quality information of the one candidate device.

26. A determination module for determining N devices to participate in the federated learning from the M candidate devices based on the network performance analysis information, where N is a positive integer equal to or smaller than M; The apparatus of claim 25 , further comprising: an execution module for establishing connections with the N devices and performing federated learning.

27. The apparatus of claim 25 , wherein the first request message includes reporting granularity indication information for instructing a device to report network performance corresponding to the candidate device as a granularity.

28. The first request message includes: A region of interest; Radio access method limited information; 26. The apparatus of claim 25, further comprising filtering information including at least one of: a.

29. The determining module is further for determining that the M candidate devices are willing to engage in federated learning; and / or 27. The apparatus of claim 26, wherein the determination module is further for determining that the M candidate devices are capable of federated learning.

30. The decision module: an acquisition submodule for acquiring federated learning willingness information of the M candidate devices from a third communication device; The apparatus of claim 29 , comprising: a determination sub-module for determining that the M candidate devices are willing to engage in federated learning based on willingness information of the M candidate devices for federated learning.

31. The decision module: an acquisition submodule for acquiring federated learning capability information of the M candidate devices from a third communication device; The apparatus of claim 29 , comprising: a determining sub-module for determining that the M candidate devices are capable of federated learning based on federated learning capability information of the M candidate devices.

32. The motivation information for the associative learning is Indication of willingness to participate in associative learning; and and condition information for participating in federated learning.

33. The condition information for participating in the federated learning is Wireless access method when participating in federated learning; Time to participate in federated learning, and a location when participating in federated learning.

34. The associative learning ability information is Models that can be used when participating in federated learning and Algorithms available for participating in federated learning, The achievable training accuracy of models when participating in federated learning, a training speed achievable for the models when participating in associative learning, the training speed indicating a training time required to train the available models to a first training accuracy; and and a size of memory space participating in the federated learning.

35. a receiving unit for receiving a first request message from the first communication device for requesting to obtain network performance analysis information; a sending unit for sending the network performance analysis information to the first communication device, the network performance analysis information including network performance analysis information corresponding to M candidate devices, where M is a positive integer; The network performance analysis information corresponding to one candidate device is Radio access method information of the one candidate device; Time information of the one candidate device available for participating in federated learning; Location information of the one candidate device; time period information covered by the network of said one candidate device; A ratio of a time period covered by the network of the one candidate device during a time period of interest to the time period of interest; and network signal quality information of the one candidate device.

36. The apparatus of claim 35 , wherein the first request message includes reporting granularity indication information for instructing a device to report network performance corresponding to the candidate device as a granularity.

37. The first request message includes: A region of interest; Radio access method limited information; 36. The apparatus of claim 35, further comprising filtering information including at least one of: a.

38. an acquiring unit for acquiring network performance data corresponding to the M candidate devices from the fourth communication device; The apparatus of claim 35 , further comprising: an analysis unit for analyzing network performance data corresponding to the M candidate devices and obtaining network performance analysis information corresponding to the M candidate devices.

39. The acquisition unit includes: A first acquisition subunit for acquiring at least one of radio access method information corresponding to the M candidate devices from a session management function network element SMF, time information covered by a network, and time information in the network of a session; and a second acquiring subunit for acquiring at least one of network identifier information, network signal quality information corresponding to the M candidate devices from a network management device.

40. The method further includes: determining the M candidate devices based on filtering information included in the first request message, and each candidate device among the M candidate devices: Located within the region of interest; The radio access method is a radio access method indicated by the radio access method limitation information; 38. The apparatus of claim 35, wherein the apparatus satisfies at least one of the conditions: being covered by a network during the time of interest.

41. a determining unit for determining that the M candidate devices are willing to engage in federated learning; and / or The apparatus of claim 35 , further comprising: a determining unit for determining that the M candidate devices are capable of federated learning.

42. The determination unit is an acquiring subunit for acquiring federated learning willingness information of the M candidate devices from a third communication device; The apparatus of claim 41 , comprising: a determining subunit for determining that the M candidate devices are willing to engage in federated learning based on willingness information of the M candidate devices for federated learning.

43. The determination unit is an acquiring subunit for acquiring federated learning capability information of the M candidate devices from a third communication device; The apparatus of claim 41 , comprising: a determining subunit for determining, based on federated learning capability information of the M candidate devices, that the M candidate devices are capable of federated learning.

44. A communications device comprising a processor and a memory, wherein the memory stores programs or commands executable by the processor, and when the programs or commands are executed by the processor, steps of the device determination method described in any one of claims 1 to 24 are realized.

45. A readable storage medium having stored thereon a program or command that, when executed by a processor, causes the steps of the device determination method according to any one of claims 1 to 24 to be realized.

46. A chip comprising a processor and a communication interface coupled thereto, the processor being adapted to execute programs or commands to implement the steps of the device determination method according to any one of claims 1 to 24.

47. A computer program product stored on a non-volatile storage medium and executed by at least one processor to implement the steps of the device determination method according to any one of claims 1 to 24.

48. 25. An electronic device arranged to carry out the steps of the device determination method according to any one of claims 1 to 24.

Images