WO2023185818A1 - 设备确定方法、装置及通信设备 - Google Patents

设备确定方法、装置及通信设备 Download PDF

Info

Publication number
WO2023185818A1
WO2023185818A1 PCT/CN2023/084339 CN2023084339W WO2023185818A1 WO 2023185818 A1 WO2023185818 A1 WO 2023185818A1 CN 2023084339 W CN2023084339 W CN 2023084339W WO 2023185818 A1 WO2023185818 A1 WO 2023185818A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
federated learning
communication device
candidate
network performance
Prior art date
Application number
PCT/CN2023/084339
Other languages
English (en)
French (fr)
Inventor
程思涵
崇卫微
Original Assignee
维沃移动通信有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 维沃移动通信有限公司 filed Critical 维沃移动通信有限公司
Publication of WO2023185818A1 publication Critical patent/WO2023185818A1/zh

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00Machine learning
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/14Session management
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W24/00Supervisory, monitoring or testing arrangements
    • H04W24/02Arrangements for optimising operational condition
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W24/00Supervisory, monitoring or testing arrangements
    • H04W24/08Testing, supervising or monitoring using real traffic

Definitions

  • the present application belongs to the field of communication technology, and specifically relates to an equipment determination method, device and communication equipment.
  • Federated learning includes horizontal federated learning and vertical federated learning.
  • horizontal federated learning increases the number of training samples by jointly participating in the same data characteristics of different samples of the equipment; vertical federated learning jointly participates in the different data characteristics of common samples of the equipment, so that the feature dimensions of the training samples are increased, so that it can be obtained A better model.
  • MF Application Function
  • NWDAF Network Data Analytics Function
  • the embodiments of this application provide a device determination method, device and communication device, which can select appropriate devices to participate in federated learning.
  • a device determination method includes: a first communication device sending a first request message to a second communication device, where the first request message is used to request obtaining network performance analysis information; the first communication device obtains network performance analysis information from the first communication device.
  • the two communication devices receive network performance analysis information.
  • 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 a candidate device includes at least one of the following information: wireless access standard information of the candidate device; time information when the candidate device can participate in federated learning; location information of the candidate device ; Information about the time period in which the candidate device has network coverage; information about the proportion of the time period in which the candidate device has network coverage to the time of interest during the time of interest; information about the network signal quality of the candidate device.
  • a device determination method includes: the second communication device receives a first request message from the first communication device, the first request message is used to request acquisition of network performance analysis information; the second communication device sends a request to the first communication device.
  • a communication device sends network performance analysis information.
  • 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 a candidate device includes at least one of the following information: wireless access standard information of the candidate device; time information when the candidate device can participate in federated learning; location information of the candidate device ;Information on the time period in which the candidate device has network coverage; within the time of interest, information on the proportion of the time period in which the candidate device has network coverage to the time of interest; information on the time period in which the candidate device has network coverage; Network signal quality information.
  • a device determination device including: a sending module, configured to send a first request message to a second communication device, where the first request message is used to request acquisition of network performance analysis information; and a receiving module, configured to obtain network performance analysis information from a second communication device.
  • the two communication devices receive network performance analysis information.
  • 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 a candidate device includes at least one of the following information: wireless access standard information of the candidate device; time information when the candidate device can participate in federated learning; location information of the candidate device ; Information about the time period in which the candidate device has network coverage; information about the proportion of the time period in which the candidate device has network coverage to the time of interest during the time of interest; information about the network signal quality of the candidate device.
  • a device determining device including: a receiving unit, configured to receive a first request message from a first communication device, where the first request message is used to request acquisition of network performance analysis information; and a sending unit, configured to send a request to the first communication device.
  • a communication device sends network performance analysis information.
  • 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 a candidate device includes at least one of the following information: wireless access standard information of the candidate device; time information when the candidate device can participate in federated learning; location information of the candidate device ; Information about the time period in which the candidate device has network coverage; information about the proportion of the time period in which the candidate device has network coverage to the time of interest during the time of interest; information about the network signal quality of the candidate device.
  • a communication device in a fifth aspect, includes a processor and a memory.
  • the memory stores a program or instructions that can be run on the processor.
  • the program or instructions are implemented when executed by the processor.
  • the device as described in the first aspect or the second aspect determines the steps of the method.
  • a communication device including a processor and a communication interface.
  • the communication interface is used to send a first request message to a second communication device; and from the second communication device Receive network performance analysis information.
  • the communication interface is used to receive the first request message from the first communication device; and to send network performance analysis information to the first communication device.
  • 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 a candidate device includes at least one of the following information: wireless access standard information of a candidate device; time information when a candidate device can participate in federated learning; location information of a candidate device; existence of a candidate device Information on the time period of network coverage; information on the proportion of the time period in which a candidate device has network coverage to the time of interest within the time of interest; information on network signal quality of a candidate device.
  • a readable storage medium is provided. Programs or instructions are stored on the readable storage medium. When the programs or instructions are executed by a processor, the device determination method as described in the first aspect or the second aspect is implemented. A step of.
  • a chip in an eighth aspect, includes a processor and a communication interface.
  • the communication interface is coupled to the processor.
  • the processor is used to run programs or instructions to implement the first aspect or the second aspect.
  • the device determines the steps of the method.
  • a computer program/program product is provided, the computer program/program product is stored in a storage medium, and the computer program/program product is executed by at least one processor to implement the first aspect or the second aspect. The steps of the device determination method described in this aspect.
  • the first communication device sends a first request message to the second communication device, and the first request message is used to request network performance analysis information; the first communication device receives the network performance analysis information from the second communication device ,
  • the network performance analysis information includes the network performance corresponding to M candidate devices, where M is a positive integer.
  • the network performance analysis information corresponding to a candidate device includes at least one of the following information: wireless access standard information of the candidate device; time information when the candidate device can participate in federated learning; location information of the candidate device ; Information about the time period in which the candidate device has network coverage; information about the proportion of the time period in which the candidate device has network coverage to the time of interest during the time of interest; information about the network signal quality of the candidate device.
  • the device due to the device’s wireless access standard information, time information that can participate in federated learning, location information, time period information with network coverage, proportion information of the time period with network coverage to the time of interest, and network
  • the signal quality information can reflect the network performance corresponding to the device. Therefore, after the first communication device receives the network performance analysis information, the first communication device can determine the network performance corresponding to each of the M candidate devices, so that the first communication device can determine the network performance corresponding to the M candidate devices.
  • a communication device can determine candidate devices that meet the network performance requirements of federated learning as devices participating in federated learning. That is, the first communication device can select an appropriate device to participate in federated learning.
  • Figure 1 is a schematic flowchart of a device determination method provided by an embodiment of the present application.
  • Figure 2 is one of the schematic diagrams of the device determination method provided by the embodiment of the present application.
  • Figure 3 is a second schematic diagram of the device determination method provided by the embodiment of the present application.
  • Figure 4 is one of the structural schematic diagrams of the equipment determination device provided by the embodiment of the present application.
  • Figure 5 is the second structural schematic diagram of the equipment determination device provided by the embodiment of the present application.
  • Figure 6 is a schematic structural diagram of a communication device provided by an embodiment of the present application.
  • Figure 7 is a hardware schematic diagram of a communication device provided by an embodiment of the present application.
  • first, second, etc. in the description and claims of this application are used to distinguish similar objects and are not used to describe a specific order or sequence. It is to be understood that the terms so used are interchangeable under appropriate circumstances so that the embodiments of the present application can be practiced in sequences other than those illustrated or described herein, and that "first" and “second” are distinguished objects It is usually one type, and the number of objects is not limited.
  • the first communication device may be one or multiple.
  • “and/or” in the description and claims indicates at least one of the connected objects, and the character “/" generally indicates that the related objects are in an "or” relationship.
  • LTE Long Term Evolution
  • LTE-Advanced, LTE-A Long Term Evolution
  • LTE-A Long Term Evolution
  • CDMA Code Division Multiple Access
  • TDMA Time Division Multiple Access
  • FDMA Frequency Division Multiple Access
  • OFDMA Orthogonal Frequency Division Multiple Access
  • SC-FDMA Single-carrier Frequency Division Multiple Access
  • NR New Radio
  • the communication devices mentioned in the embodiments of this application may be core network devices, and may also be called network elements. , or network node.
  • the core network equipment may include but is not limited to at least one of the following: core network nodes, core network functions, application functions (Application Function, AF), data network analysis functions (Network Data Analytics Function, NWDAF), unified data management (Unified Data Management (UDM), Network Exposure Function (NEF), Local NEF (Local NEF, or L-NEF), Operation Administration and Maintenance (OAM), User Plane Function, UPF), session management function (Session Management Function, SMF), data collection application function (Data Collection-Application Function, DC-AF), mobility management entity (Mobility Management Entity, MME), access mobility management function (Access andMobility Management Function (AMF), User Plane Function (UPF), Policy Control Function (PCF), Policy and Char
  • terminals may include terminals (which may also be called terminal devices or user equipment (User Equipment, UE)), or any other possible devices.
  • the terminal may be a mobile phone, a tablet computer (Tablet Personal Computer), Laptop Computer (Laptop Computer), also known as Notebook Computer, Personal Digital Assistant (Personal Digital Assistant, PDA), Palm Computer, Netbook, Ultra-Mobile Personal Computer (UMPC), Mobile Internet Device (Mobile Internet Device, MID), Augmented Reality (AR)/Virtual Reality (VR) equipment, robots, wearable devices (Wearable Device), vehicle-mounted equipment (VUE), pedestrian terminals (PUE), smart homes ( Home equipment with wireless communication functions, such as refrigerators, TVs, washing machines or furniture, etc.), game consoles, personal computers (PCs), teller machines or self-service machines and other terminal-side devices.
  • PCs personal computers
  • teller machines or self-service machines and other terminal-side devices such as refrigerators, TVs, washing machines or furniture, etc.
  • Wearable devices include: smart watches, smart phones, etc. Bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. It should be noted that in this application The embodiment does not limit the specific type of terminal.
  • this embodiment of the present application provides a device determination method, which may include the following steps 201 to 204.
  • Step 201 The first communication device sends a first request message to the second communication device.
  • Step 202 The second communication device receives the first request message from the first communication device.
  • the above-mentioned first request message may be used to request to obtain network performance analysis information.
  • Step 203 The second communication device sends network performance analysis information to the first communication device.
  • Step 204 The first communication device receives network performance analysis information from the second communication device.
  • 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 a candidate device may include at least one of the following information:
  • the second communication device can send the network performance analysis information corresponding to the M candidate devices to the first communication device, so that the first communication device can obtain The network performance of each candidate device among the M candidate devices can then determine the candidate device that meets the network performance requirements of federated learning as a device participating in federated learning. That is, the first communication device can select an appropriate candidate device for federation. study.
  • the network performance analysis information can indicate the network performance corresponding to M candidate devices
  • the first communication device can obtain each of the M candidate devices. Network performance corresponding to each candidate device, so that the first communication device can determine the candidate device that meets the network performance requirements of federated learning as a device participating in federated learning.
  • the first communication device may include an AF or any other possible service consumer entity; the second communication device may include an NWDAF; and the candidate device may include a UE or any other possible device.
  • the details may be determined according to actual usage requirements, which are not limited in the embodiments of this application.
  • the wireless access standard may be a non-third generation partnership project (non 3GPP) wireless access standard, such as wireless local area networks (WLAN), or it may be 3GPP's wireless access instructions, such as the fourth generation (4G) evolved UMTS terrestrial radio access network (evolved universal terrestrial radio access network (EUTRAN or E-UTRAN)), or the fifth generation communication technology (fifth generation, 5G) NR, etc.
  • 4G fourth generation evolved UMTS terrestrial radio access network
  • EUTRAN or E-UTRAN evolved universal terrestrial radio access network
  • 5G fifth generation communication technology
  • the wireless access mode information of a candidate device may indicate that the wireless access mode of the candidate device is non-3GPP WLAN.
  • the time information at which a candidate device can participate in federated learning may indicate the time at which the candidate device can participate in federated learning, such as 00:00-04:00 every day.
  • the location information of a candidate device may indicate the area, cell or tracking area (TA) where the candidate device is located.
  • the above-mentioned time of interest may be a time that the first communication device is interested in, such as a time when the first communication device plans to perform federated learning. For example, First Communications Equipment plans to conduct federated learning from 01:00 to 03:00 on March 15, 2020.
  • the time period information in which a candidate device has network coverage may indicate the duration or time period in which the candidate device has network coverage.
  • the proportion information of the time period in which a candidate device has network coverage to the time of interest (hereinafter referred to as the network coverage time proportion information) can indicate that the candidate device is within the time of interest.
  • the candidate device taking the candidate device as a terminal and the wireless access standard as Wireless Local Area Networks (WLAN), it is assumed that the time of interest is 3 hours from 8:00 to 11:00, and the terminal is in these 3 hours. If there is wireless fidelity (Wi-Fi) coverage for 2 hours within 2 hours, then the terminal has Wi-Fi coverage. The time period accounts for 2/3 of the time of interest.
  • Wi-Fi wireless fidelity
  • the network coverage time proportion information can indicate the proportion of the time period in which the candidate device has network coverage to the time of interest through levels, such as but not limited to "high, medium, low"; or , The network coverage time proportion information can also indicate the proportion of the time period in which the candidate device has network coverage to the time of interest in the form of decimals, fractions, or percentages. The details can be determined according to actual usage requirements, and are not limited in the embodiments of this application.
  • the network signal quality information is used to indicate the network signal quality of the device.
  • Network signal quality may include at least one of signal quality, signal strength, and signal stability.
  • the network signal quality can be represented by the average value or peak value of the network signal quality parameters.
  • the network signal can be represented by at least one parameter of received signal strength indication (RSSI) and path return time (round trip time, RTT). quality.
  • RSSI received signal strength indication
  • RTT round trip time
  • the above-mentioned first request message may include reporting granularity indication information, and the reporting granularity indication information may be used to instruct network performance analysis information corresponding to the candidate device to be reported at the device granularity.
  • the reporting granularity indication information indicates that the network performance analysis information corresponding to the candidate UE is reported with UE (per UE) as the granularity.
  • the first communication device can determine the network performance of each UE among the M candidate UEs, so that a suitable UE can be selected to participate in federated learning.
  • the above-mentioned first request information may include filtering information, and the filtering information may include at least one of the following:
  • Area of interest which can also be called an area of interest, such as one or more cells, or one or more tracking areas (TA).
  • area of interest such as one or more cells, or one or more tracking areas (TA).
  • TA tracking areas
  • Wireless access standard limitation information which may be used to indicate the wireless access standard of the candidate device.
  • the wireless access standard please refer to the relevant description of the above embodiments.
  • the interesting time may be the time when the first communication device plans to perform federated learning. For example, 00:00-04:00 on March 15, 2020, the specific time can be determined based on actual usage needs.
  • the above filtering information may also include at least one of the following:
  • the network signal quality limitation information can be used to indicate the required network signal quality threshold of the candidate device.
  • the network signal quality threshold can be the minimum requirement for the network signal quality of the candidate device.
  • the candidate device is required to operate within 90% of the time of interest. % and above, the signal strength can reach the target value.
  • the algorithm qualification information can be used to indicate the algorithms related to machine learning and other artificial intelligence (artificial intelligence, AI) data analysis tasks supported by the required candidate device, such as deep learning, linear regression, etc.
  • AI artificial intelligence
  • the training accuracy limit information of the model can be used to indicate the achievable training accuracy of the model that can be used when the required candidate device participates in federated learning. That is, the usable model can reach after the training is completed. model accuracy. That is, after the training of the model is completed, the number of correct predictions (judgments) accounts for the proportion of the total number of predictions, Such as 90% accuracy.
  • the training speed limit information of the model can be used to indicate the model that can be used when the required candidate device will participate in federated learning, and is trained to the first training accuracy (for example, 80% accuracy). training time. Specifically, it can be the training time required for the model to reach the first training accuracy when the candidate device locally trains the model. The longer the training time required, the slower the training speed; the shorter the training time required, the faster the training speed.
  • Storage space limitation information for federated learning is used to indicate the storage space size of models, data and other information reserved for federated learning by the required candidate device, for example, 10 megabits (MB).
  • the above-mentioned first request message may also include an analytic identifier (analytic ID) of network performance.
  • the analytic identifier may be used to indicate the task corresponding to the first request message, such as this time.
  • the task is to obtain the network performance of candidate devices that meet the requirements of filtering information.
  • the network performance analysis identifier may be WLAN performance (performance) or NRperformance.
  • the first request message may also include reporting limitation information, and the reporting limitation information may be at least one of the following:
  • the sorting information is used to instruct the second communication device to output the candidate devices in ascending or descending order according to a certain parameter/scale. Assuming that the output is in descending order of signal strength, then when the second communication device returns the result (that is, sends the network performance analysis information to the first communication device), the candidate devices can be arranged in order from small to large signal strength.
  • the grouping information is used to instruct the second communication device to group the candidate devices according to certain parameters/factors (such as time, location, etc.). For example, the second communication device may group candidate devices that perform federated learning from 10:00 to 12:00 during the day among all candidate devices.
  • the device determination method provided by the embodiment of this application uses the device's wireless access standard information, time information that can participate in federated learning, location information, network coverage time period information, and network coverage time period accounting for the time of interest.
  • the proportion information and the network signal quality information can both reflect the network performance corresponding to the device. Therefore, after the first communication device receives the network performance analysis information, the first communication device can determine that each of the M candidate devices corresponds to network performance, so that the first communication device can determine candidate devices that meet the network performance requirements of federated learning as devices participating in federated learning, that is, the first communication device can select appropriate devices to participate in federated learning.
  • the device determination method provided by the embodiment of the present application may also include the following steps 205 and 206.
  • Step 205 The first communication device determines N devices participating in federated learning from M candidate devices based on the network performance analysis information, where N is a positive integer less than or equal to M.
  • Step 206 The first communication device establishes connections with N devices and performs federated learning.
  • the first communication device may N devices participating in federated learning are determined from the above M candidate devices, and then connections can be established with the N devices and federated learning can be performed, so that a federated learning model that meets the requirements of the first communication device can be obtained.
  • the first communication device limits UEs that need to connect to WLAN and whose signal strength needs to reach a threshold, and limits federated learning to be performed within city A on March 15, 2020.
  • the above M candidate UEs are UEs that meet these conditions.
  • the first communication device can be selected based on the number of UE time overlaps on March 15, 2020. For example, between 2:00 and 3:00 pm on March 15, 2020, 500 UEs that meet the conditions can participate in federated learning, and From 2 pm to 3 pm is the time with the largest number of UE time overlaps that day, then the first communication device can use the 500 UEs as devices participating in federated learning.
  • the first communication device can establish connections with the 500 UEs from 2:00 to 3:00 pm on March 15, 2020, and perform federated learning.
  • the first communication device may select the UE with the best network signal strength as a device participating in federated learning.
  • the device determination method provided by the embodiment of the present application may further include at least one of the following steps 207 and 208.
  • Steps 207 and 208 can be executed before the above-mentioned step 201 or after step 204.
  • the details can be determined according to actual usage requirements.
  • the embodiments of this application are not limiting.
  • Step 207 The first communication device determines that M candidate devices have federated learning willingness.
  • Step 208 The first communication device determines that the M candidate devices have federated learning capabilities.
  • the first communication device may first determine whether the M candidate devices have the willingness to federated learning. and/or federated learning capabilities. When it is determined that M candidate devices have federated learning willingness and/or federated learning capabilities, N devices participating in federated learning can be determined from the M candidate devices.
  • step 207 can be implemented through the following steps 207a and 207b.
  • Step 207a The first communication device obtains federated learning willingness information of M candidate devices from the third communication device.
  • Step 207b The first communication device determines that the M candidate devices have federated learning willingness based on the federated learning willingness information of the M candidate devices.
  • the first communication device can determine the M candidates based on the federated learning willingness information of the M candidate devices.
  • the device has federated learning capabilities.
  • the first communication device obtains the federated learning intention information of Q devices from the third communication device, and filters the M candidate devices from the federated learning intention information of the Q devices.
  • Federal Learning Intent Information It can be understood that the Q devices may include M candidate devices.
  • the third communication device may be a UDM.
  • the above-mentioned federated learning intention information may include at least one of the following:
  • condition information for participating in federated learning may include at least one of the following:
  • Wireless access standard when participating in federated learning such as non-3GPP WLAN
  • the time to participate in federated learning that is, the time when you can participate in federated learning, such as 2:00-5:00 in the morning;
  • the location when participating in federated learning such as the area or the connected community when participating in federated learning.
  • step 208 can be implemented through the following steps 208a and 208b.
  • Step 208a The first communication device obtains federated learning capability information of M candidate devices from the third communication device.
  • Step 208b The first communication device determines that the M candidate devices have federated learning capabilities based on the federated learning capability information of the M candidate devices.
  • the first communication device may determine the M candidates based on the federated learning capability information of the M candidate devices.
  • the device has federated learning capabilities.
  • the first communication device obtains the federated learning intention information of S devices from the third communication device, and filters the M candidate devices from the federated learning intention information of the S devices.
  • Federal Learning Intent Information It can be understood that S devices may include M candidate devices.
  • the above federated learning capability information may include at least one of the following:
  • Models that can be used when participating in federated learning such as models using specific network architectures, such as Residual Networks (ResNet), Inception-v3, etc.
  • Residual Networks Residual Networks (ResNet)
  • Inception-v3 models using specific network architectures, such as Residual Networks (ResNet), Inception-v3, etc.
  • Algorithms that can be used when participating in federated learning, such as gradient descent, etc.
  • the training accuracy of the model that can be achieved when participating in federated learning that is, the model accuracy that the usable model can achieve after the training of the usable model is completed, such as the highest accuracy that can be achieved. That is, after the training of the model is completed, the proportion of the number of correct predictions and judgments to the total number, such as the accuracy rate is 90%.
  • the training speed of the model that can be achieved when participating in federated learning is used to indicate the training time required to train the model that can be used when participating in federated learning to the first training accuracy. That is, the first device locally trains the model that can be used.
  • the training time for example, 30 minutes
  • the training time for example, 80%
  • the longer the training time the slower the training speed; the shorter the training time, the faster the training speed.
  • the size of the storage space participating in federated learning that is, the size of the storage space reserved for federated learning models, data and other information, such as 15MB.
  • the device determination method provided by the embodiment of the present application may also include the following step 209.
  • Step 209 The first communication device obtains the network function opening information of the third communication device from the fifth communication device.
  • the above-mentioned fifth communication device may be an NEF or other communication device, and the details may be determined according to actual usage requirements.
  • the first communication device may send the second request information to the fifth communication device to request to obtain the opening information of the network function of the third communication device, so that it can interact with the third communication device.
  • the first communication device may obtain the federated learning willingness information of the M candidate devices and/or the federated learning capability information of the M candidate devices from the above-mentioned third communication device.
  • the device determination method provided by the embodiment of the present application may further include the following steps 210 and 211.
  • Step 210 The second communication device obtains the corresponding network performance data of the M candidate devices from the fourth communication device.
  • Step 211 The second communication device analyzes the network performance data corresponding to the M candidate devices, and obtains the network performance analysis information corresponding to the M candidate devices.
  • the second communication device can obtain the network performance data corresponding to the M candidate devices from the fourth communication device, and then analyze the network performance data corresponding to the M candidate devices, so that the M candidate devices can be obtained Corresponding network performance analysis information.
  • the fourth communication device may include at least one of network elements such as SMF, OAM, UDM, and DC-AF.
  • the above step 210 may be implemented by at least one of the following steps 210a and 210b.
  • Step 210a The second communication device obtains at least one of: wireless access standard information, network coverage time information, and session time information in the network corresponding to the M candidate devices from the SMF;
  • Step 210b The second communication device obtains at least one of network identification information and network signal quality information corresponding to the M candidate devices from the network management device.
  • NWDAF can obtain the network signal quality information corresponding to the M candidate devices from OAM, such as the signal quality information of the device connected to WLAN (such as RTT, RSSI, etc.), and obtain it from OAM.
  • the network identification information corresponding to the M candidate devices such as Service Set Identifier (SSID), etc.; obtain the wireless access standard information corresponding to the M candidate devices from the SMF, such as WLAN, 5G NR, or 4G EUTRAN, etc., and Obtain network coverage time information corresponding to M candidate devices from SMF, such as WLAN coverage time; obtain algorithm information supported by M candidate devices, achievable model training accuracy information, etc. from UDM or DCAF; and obtain M from UPF Traffic information corresponding to each candidate device, etc.
  • SSID Service Set Identifier
  • the second communication device can analyze the network performance data of the M candidate devices, thereby obtaining the M candidate devices.
  • the network performance analysis results of the M candidate devices can be used to generate network performance analysis information corresponding to the M candidate devices based on the network performance analysis results of the M candidate devices.
  • the following is an exemplary explanation of the network performance analysis results of the device based on Table 1, taking the wireless access mode of the device as WLAN as an example.
  • the device determination method provided by the embodiment of the present application may further include the following step 212.
  • Step 212 The second communication device determines M candidate devices according to the filtering information included in the first request message.
  • each candidate device among the M candidate devices meets at least one of the following conditions:
  • the wireless access standard is the wireless access standard indicated by the wireless access standard qualification information
  • each of the M candidate devices mentioned above may also meet at least one of the following conditions:
  • the network signal quality is greater than or equal to the network signal quality indicated by the network signal quality limit information
  • the supported algorithms are those indicated by the algorithm qualification information;
  • the training accuracy of the model that can be achieved when participating in federated learning is greater than or equal to 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 federated learning is greater than or equal to the training speed indicated by the model's training speed limit information
  • the storage space size participating in federated learning is greater than or equal to the storage space size indicated by the storage space limit information of federated learning.
  • the training accuracy indicated by the training accuracy limit information of the above model is 85%
  • the training accuracy of the model that can be achieved when one of the above K devices is used with federated learning is 93%
  • the training accuracy can be Devices can be identified as candidate devices.
  • the device determination method provided by the embodiment of the present application may also include the following step 213 and/or step 214.
  • Step 213 The second communication device determines that the M candidate devices have federated learning willingness.
  • Step 214 The second communication device determines that the M candidate devices have federated learning capabilities.
  • the first communication device may first determine whether the M candidate devices have federated learning willingness and/or federated learning capabilities. When a candidate device has a federated learning willingness and/or a federated learning capability, the network performance analysis information corresponding to the M candidate devices may be sent to the first communication device.
  • step 213 can be implemented through the following steps 213a and 213b.
  • Step 213a The second communication device obtains federated learning willingness information of M candidate devices from the third communication device.
  • Step 213b The second communication device determines that the M candidate devices have federated learning willingness based on the federated learning willingness information of the M candidate devices.
  • the first communication device can determine the M candidates based on the federated learning willingness information of the M candidate devices.
  • the device has a federated learning willingness, so that the network performance analysis information corresponding to the M candidate devices that have a federated learning willingness can be sent to the first communication device. In this way, the first communication device can directly select from the M candidate devices.
  • the corresponding devices participate in federated learning.
  • the above-mentioned second communication device obtains the federated learning intention information of W devices from the third communication device, and filters the M candidate devices from the federated learning intention information of the W devices.
  • Federal Learning Intent Information It can be understood that W devices may include M candidate devices.
  • the third communication device may be a UDM.
  • step 214 can be implemented through the following steps 214a and 214b.
  • Step 214a The second communication device obtains the federated learning capability information of the M candidate devices from the third communication device.
  • Step 214b The second communication device determines that the M candidate devices have federated learning capabilities based on the federated learning capability information of the M candidate devices.
  • the first communication device can determine the M candidates based on the federated learning capability information of the M candidate devices.
  • the device has the federated learning capability, so that the network performance analysis information corresponding to the M candidate devices with the federated learning capability can be sent to the first communication device. In this way, the first communication device can directly select a corresponding device from the M candidate devices to participate in federated learning.
  • the above-mentioned second communication device obtains the federated learning capability information of P devices from the third communication device, and screens the above-mentioned M candidate devices from the federated learning willingness capabilities of the P devices.
  • Federal learning capability information It can be understood that P devices may include M candidate devices.
  • the device determination method provided by the embodiment of the present application may also include the following step 215.
  • Step 215 The second communication device obtains the network function opening information of the third communication device from the fifth communication device.
  • the above-mentioned fifth communication device may be an NEF or other communication device, and the details may be determined according to actual usage requirements.
  • the second communication device may send second request information to the fifth communication device to request to obtain the opening information of the network function of the third communication device, so that it can interact with the third communication device.
  • the second communication device may obtain the federated learning willingness information of the M candidate devices and/or the federated learning capability information of the M candidate devices from the above-mentioned third communication device.
  • the device determination method provided by the embodiment of the present application will be exemplarily described below with reference to FIG. 2 and FIG. 3 .
  • step 0a Service consumers such as AF send requests to NEF to obtain network function opening information about communication devices such as UDM/NRF/DCAF, in order to later obtain the federated learning intention of candidate devices from communication devices such as UDM information and/or federated learning capability information to determine whether the device has federated learning capabilities and/or federated learning willingness.
  • Service consumers such as AF send requests to NEF to obtain network function opening information about communication devices such as UDM/NRF/DCAF, in order to later obtain the federated learning intention of candidate devices from communication devices such as UDM information and/or federated learning capability information to determine whether the device has federated learning capabilities and/or federated learning willingness.
  • Step 0b Service consumers such as AF request federated learning willingness information and/or federated learning capability information from capability storage network elements such as UDM/NRF/DC-AF.
  • step 1 Service consumers such as AF send a first request message to NWDAF (you can use Nnwdaf_AnalyticsInfo or Nnwdaf_AnalyticsSubscription) to request network performance analysis information.
  • NWDAF you can use Nnwdaf_AnalyticsInfo or Nnwdaf_AnalyticsSubscription
  • Step 2 Based on the task description and limiting conditions of the first request message, NWDAF obtains network performance data such as the UE's wireless connection format and signal quality from data providers such as SMF, OAM, and UDM. Among them, step 2 can include Including step 2a, step 2b and step 2c.
  • Step 3 NWDAF uses the obtained network performance data for analysis to obtain network performance analysis results at UE granularity, thereby obtaining network performance analysis information.
  • Step 4 NWDAF returns a task response message based on the description information of the first request message in step 1, that is, it sends network performance analysis information to service consumers such as AF. NWDAF can respond accordingly based on the Nnwdaf_AnalyticsInfo or Nnwdaf_AnalyticsSubscription used in step 1.
  • Step 5 Service consumers such as AF determine the UE(s) participating in federated learning based on the response message returned in step 4.
  • Step 6 Service consumers such as AF establish a connection with the UE(s) based on the identification information of the UE(s) participating in federated learning determined in step 5, and perform federated learning.
  • the execution subject may also be a device determination device.
  • the device determination device executing the device determination method is taken as an example to illustrate the device determination device provided by the embodiment of the present application.
  • the federated learning device acquisition device 300 includes a sending module 301 and a receiving module 302.
  • the sending module 301 is used to send a first request message to the second communication device, and the first request message is used to request to obtain network performance analysis information;
  • the receiving module 302 is used to receive the network performance analysis information from the second communication device, and the network performance analysis
  • the information includes network performance analysis information corresponding to M candidate devices, where M is a positive integer.
  • the network performance analysis information corresponding to a candidate device includes at least one of the following information: wireless access standard information of a candidate device; time information when a candidate device can participate in federated learning; location information of a candidate device; Information about the time period in which the device has network coverage; within the time of interest, information about the proportion of the time period in which a candidate device has network coverage to the time of interest; information about the network signal quality of a candidate device.
  • the device determination device also includes a determination module and an execution module; a determination module, configured to determine N devices participating in federated learning from M candidate devices based on network performance analysis information, where N is a positive integer less than or equal to M. ; Execution module, used to establish connections with N devices and perform federated learning.
  • the first request message includes reporting granularity indication information, and the reporting granularity indication information is used to indicate that the network performance corresponding to the candidate device is reported at the device granularity.
  • the first request message includes filtering information, and the filtering information includes at least one of the following:
  • the determining module is also used to determine that the M candidate devices have federated learning willingness; and/or the determining module is also used to determine that the M candidate devices have federated learning capabilities.
  • the determining module includes an obtaining sub-module and a determining sub-module; the obtaining sub-module is used to obtain the federated learning intention information of the M candidate devices from the third communication device; and the determining sub-module is used to obtain the federated learning intention information of the M candidate devices from the third communication device.
  • Learning willingness information determines that M candidate devices have federated learning willingness.
  • the determining module includes an obtaining sub-module and a determining sub-module; the obtaining sub-module is used to obtain the federated learning capability information of the M candidate devices from the third communication device; and the determining sub-module is used to obtain the federated learning capability information of the M candidate devices from the third communication device.
  • Learning capability information determines that M candidate devices have federated learning capabilities.
  • the federal study intention information includes at least one of the following:
  • condition information for participating in federated learning includes at least one of the following:
  • the federal learning capability information includes at least one of the following:
  • the training speed of the model that can be achieved when participating in federated learning.
  • the training speed is used to indicate the training time required to train a usable model to the first training accuracy;
  • the above-mentioned second communication device includes NWDAF.
  • Embodiments of the present application provide a device for determining equipment. Since the wireless access standard information of the device, time information that can participate in federated learning, location information, time period information with network coverage, and time period with network coverage account for the interests of interest. The time proportion information and the network signal quality information can reflect the network performance corresponding to the device. Therefore, after receiving the network performance analysis information, the device determining device can determine the network performance corresponding to each of the M candidate devices, Therefore, candidate devices that meet the network performance requirements of federated learning can be determined as devices participating in federated learning, that is, the device determining device can select appropriate devices to participate in federated learning.
  • this embodiment of the present application provides a device determination device 400 , which includes a receiving unit 401 and a sending unit 402 .
  • the receiving unit 401 may be configured to receive a first request message from the first communication device.
  • the first request message is used to request acquisition of network performance analysis information;
  • the sending unit is configured to send network performance analysis information to the first communication device.
  • the first request message is used to request network performance analysis information.
  • the information includes network performance analysis information corresponding to M candidate devices, where M is a positive integer.
  • the network performance analysis information corresponding to a candidate device includes at least one of the following information: wireless access standard information of the candidate device; time information when the candidate device can participate in federated learning; location information of the candidate device ; Information about the time period in which the candidate device has network coverage; information about the proportion of the time period in which the candidate device has network coverage to the time of interest during the time of interest; information about the network signal quality of the candidate device.
  • the first request message includes reporting granularity indication information, and the reporting granularity indication information is used to indicate that the network performance corresponding to the candidate device is reported at the device granularity.
  • the first request message includes filtering information, and the filtering information includes at least one of the following:
  • the device determining device further includes an acquisition unit and an analysis unit.
  • the acquisition unit is used to obtain the corresponding network performance data of the M candidate devices from the fourth communication device;
  • the analysis unit is used to analyze the network performance data corresponding to the M candidate devices to obtain the network performance data corresponding to the M candidate devices. Performance analysis information.
  • the obtaining unit includes a first obtaining subunit and a second obtaining subunit; the first obtaining subunit is used to obtain: wireless access standard information corresponding to the M candidate devices from the session management function network element SMF, At least one of network coverage time information and session time information in the network; the second acquisition subunit is used to obtain: network identification information and network signal quality information corresponding to the M candidate devices from the network management device at least one of them.
  • the device determining device further includes a determining unit; the determining unit is configured to determine the M candidate devices according to the filtering information included in the first request message, wherein each of the M candidate devices Candidate devices meet at least one of the following conditions:
  • the wireless access standard is the wireless access standard indicated by the wireless access standard qualification information
  • the device determining device further includes a determining unit; a determining unit used to determine that the M candidate devices have federated learning willingness; and/or a determining unit used to determine that the M candidate devices have federated learning capabilities.
  • the determining unit includes an obtaining subunit and a determining subunit; the obtaining subunit is used to obtain the federated learning intention information of the M candidate devices from the third communication device; and the determining subunit is used to obtain the federated learning intention information of the M candidate devices from the third communication device.
  • Learning willingness information determines that M candidate devices have federated learning willingness.
  • the determining unit includes an obtaining subunit and a determining subunit; the obtaining subunit is used to obtain the federated learning capability information of the M candidate devices from the third communication device; and the determining subunit is used to obtain the federated learning capability information of the M candidate devices from the third communication device.
  • Learning capability information determines that M candidate devices have federated learning capabilities.
  • the federal study intention information includes at least one of the following:
  • condition information for participating in federated learning includes at least one of the following:
  • the federal learning capability information includes at least one of the following:
  • the training speed of the model that can be achieved when participating in federated learning.
  • the training speed is used to indicate the training time required to train a usable model to the first training accuracy;
  • Embodiments of the present application provide a device determination device based on the device's wireless access standard information, time information that can participate in federated learning, location information, time period information with network coverage, and the time period with network coverage accounting for the time of interest.
  • the proportion information and the network signal quality information can reflect the network performance corresponding to the device. Therefore, after the device determining device sends the network performance analysis information to the first communication device, the first communication device can determine each of the M candidate devices.
  • the network performance corresponding to each candidate device can enable the first communication device to determine the candidate device that meets the network performance requirements of federated learning as a device participating in federated learning, that is, the first communication device can select an appropriate device to participate in federated learning. .
  • the device determining device in the embodiment of the present application may be an electronic device, such as an electronic device with an operating system, or may be a component in the electronic device, such as an integrated circuit or chip.
  • the electronic device may be a terminal or other devices other than the terminal.
  • the terminal may include but is not limited to the types of terminal 11 listed above, and other devices may be servers, network attached storage (Network Attached Storage, NAS), etc., in the embodiment of the present application No specific limitation is made.
  • the equipment determination device provided by the embodiments of the present application can implement each process implemented by the above method embodiments and achieve the same technical effect. To avoid duplication, the details will not be described here.
  • this embodiment of the present application also provides a communication device 500, which includes a processor 501 and a memory 502.
  • the memory 502 stores programs or instructions that can be run on the processor 501, for example, the When the communication device 500 is the first communication device, when the program or instruction is executed by the processor 501, each step of the above device determination method embodiment is implemented, and the same technical effect can be achieved.
  • the communication device 500 is a second communication device, when the program or instruction is executed by the processor 501, each step of the above device determination method embodiment is implemented, and the same technical effect can be achieved. To avoid duplication, the details are not repeated here.
  • An embodiment of the present application also provides a communication device, including a processor and a communication interface.
  • the communication interface is used to send a first request message to a second communication device; and from the second communication device Receive network performance analysis information.
  • the communication interface is used to receive the first request message from the first communication device; and to send network performance analysis information to the first communication device.
  • 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 a candidate device includes at least one of the following information: wireless access standard information of a candidate device; time information when a candidate device can participate in federated learning; location information of a candidate device; existence of a candidate device Information on the time period of network coverage; information on the proportion of the time period in which a candidate device has network coverage to the time of interest within the time of interest; information on network signal quality of a candidate device.
  • This communication device embodiment corresponds to the above-mentioned first communication device or second communication device method embodiment. Each implementation process and implementation manner of the above-mentioned method embodiment can be applied to this communication device embodiment, and can achieve the same technical effect. .
  • the embodiment of the present application also provides a communication device.
  • the communication device 600 includes: a processor 601 , a network interface 602 and a memory 603 .
  • the network interface 602 is, for example, a common public radio interface (CPRI).
  • CPRI common public radio interface
  • the communication device 600 in the embodiment of the present invention also includes: instructions or programs stored in the memory 603 and executable on the processor y01.
  • the processor 601 calls the instructions or programs in the memory y03 to execute the execution of each module in the device determination device. method and achieve the same technical effect. To avoid duplication, we will not repeat it here.
  • Embodiments of the present application also provide a readable storage medium. Programs or instructions are stored on the readable storage medium. When the program or instructions are executed by a processor, each process of the above device determination method embodiment is implemented, and the same technology can be achieved. The effect will not be described here to avoid repetition.
  • Readable storage media includes computer-readable storage media, such as computer read-only memory ROM, random access memory RAM, magnetic disks or optical disks.
  • the embodiment of the present application also provides a chip.
  • the chip includes a processor and a communication interface.
  • the communication interface is coupled to the processor.
  • the processor is used to run programs or instructions to implement each process of the above device determination method embodiment, and can achieve the same To avoid repetition, the technical effects will not be repeated here.
  • chips mentioned in the embodiments of this application may also be called system-on-chip, system-on-a-chip, system-on-chip or system-on-chip, etc.
  • Embodiments of the present application further provide a computer program/program product.
  • the computer program/program product is stored in a storage medium.
  • the computer program/program product is executed by at least one processor to implement each process of the above device determination method embodiment. And can achieve the same technical effect. To avoid repetition, they will not be described again here.
  • the methods of the above embodiments can be implemented by means of software plus the necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is better. implementation.
  • the technical solution of the present application can be embodied in the form of a computer software product that is essentially or contributes to the existing technology.
  • the computer software product is stored in a storage medium (such as ROM/RAM, disk , CD), including several instructions to cause a terminal (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods of various embodiments of the present application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本申请公开了一种设备确定方法、装置及通信设备,该设备确定方法包括:第一通信设备向第二通信设备发送第一请求消息,第一请求消息用于请求获取网络性能分析信息;第一通信设备从第二通信设备接收网络性能分析信息,网络性能分析信息包括M个候选设备对应的网络性能分析信息。一个候选设备对应的网络性能分析信息包括以下至少一种信息:一个候选设备的无线接入制式信息;一个候选设备可参与联邦学习的时间信息;一个候选设备的所处位置信息;一个候选设备存在网络覆盖的时间段信息;在感兴趣时间内,一个候选设备存在网络覆盖的时间段占感兴趣时间的比例信息;一个候选设备的网络信号质量信息。

Description

设备确定方法、装置及通信设备
本申请要求于2022年3月28日提交国家知识产权局、申请号为202210314847.1、申请名称为“设备确定方法、装置及通信设备”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请属于通信技术领域,具体涉及一种设备确定方法、装置及通信设备。
背景技术
随着通信技术的发展,联邦学习也应运而生。联邦学习包括横向联邦学习和纵向联邦学习。其中,横向联邦学习通过联合参与设备的不同样本的相同数据特征,使得训练样本的数量增多;纵向联邦学习通过联合参与设备的共同样本的不同数据特征,使得训练样本的特征维度增多,从而可以得到一个更好的模型。
“成员选择”对于联邦学习尤为重要,选择合适的设备(比如用户设备(User Equipment,UE)等)进行联邦学习,可以提高训练效率,相反,选择不合适的设备进行联邦学习,则会影响训练效率和训练结果。以服务消费者设备(例如应用功能(Application Function,AF)进行联邦学习为例。通常,AF可以根据数据网络分析功能(Network Data Analytics Function,NWDAF)上报的某一区域(比如某地区或某小区)对应的网络性能,选择该区域中的一些设备进行联邦学习。然而由于同一区域中的不同设备对应的网络性能存在差异,因此如何选择合适的设备参与联邦学习成为一个亟待解决的问题。
发明内容
本申请实施例提供一种设备确定方法、装置及通信设备,能够选择合适的设备参与联邦学习。
第一方面,提供了一种设备确定方法,该方法包括:第一通信设备向第二通信设备发送第一请求消息,第一请求消息用于请求获取网络性能分析信息;第一通信设备从第二通信设备接收网络性能分析信息,网络性能分析信息包括M个候选设备对应的网络性能分析信息,M为正整数。其中,一个候选设备对应的网络性能分析信息包括以下至少一种信息:该一个候选设备的无线接入制式信息;该一个候选设备可参与联邦学习的时间信息;该一个候选设备的所处位置信息;该一个候选设备存在网络覆盖的时间段信息;在感兴趣时间内,该一个候选设备存在网络覆盖的时间段占感兴趣时间的比例信息;该一个候选设备的网络信号质量信息。
第二方面,提供了一种设备确定方法,该方法包括:第二通信设备从第一通信设备接收第一请求消息,第一请求消息用于请求获取网络性能分析信息;第二通信设备向第一通信设备发送网络性能分析信息,网络性能分析信息包括M个候选设备对应的网络性能分析信息,M为正整数。其中,一个候选设备对应的网络性能分析信息包括以下至少一种信息:该一个候选设备的无线接入制式信息;该一个候选设备可参与联邦学习的时间信息;该一个候选设备的所处位置信息;该一个候选设备存在网络覆盖的时间段信息;在感兴趣时间内,该一个候选设备存在网络覆盖的时间段占感兴趣时间的比例信息;该一个候选设备的 网络信号质量信息。
第三方面,提供了一种设备确定装置,包括:发送模块,用于向第二通信设备发送第一请求消息,第一请求消息用于请求获取网络性能分析信息;接收模块,用于从第二通信设备接收网络性能分析信息,网络性能分析信息包括M个候选设备对应的网络性能分析信息,M为正整数。其中,一个候选设备对应的网络性能分析信息包括以下至少一种信息:该一个候选设备的无线接入制式信息;该一个候选设备可参与联邦学习的时间信息;该一个候选设备的所处位置信息;该一个候选设备存在网络覆盖的时间段信息;在感兴趣时间内,该一个候选设备存在网络覆盖的时间段占感兴趣时间的比例信息;该一个候选设备的网络信号质量信息。
第四方面,提供了一种设备确定装置,包括:接收单元,用于从第一通信设备接收第一请求消息,第一请求消息用于请求获取网络性能分析信息;发送单元,用于向第一通信设备发送网络性能分析信息,网络性能分析信息包括M个候选设备对应的网络性能分析信息,M为正整数。其中,一个候选设备对应的网络性能分析信息包括以下至少一种信息:该一个候选设备的无线接入制式信息;该一个候选设备可参与联邦学习的时间信息;该一个候选设备的所处位置信息;该一个候选设备存在网络覆盖的时间段信息;在感兴趣时间内,该一个候选设备存在网络覆盖的时间段占感兴趣时间的比例信息;该一个候选设备的网络信号质量信息。
第五方面,提供了一种通信设备,该通信设备包括处理器和存储器,所述存储器存储可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执行时实现如第一方面或第二方面所述的设备确定方法的步骤。
第六方面,提供了一种通信设备,包括处理器及通信接口,其中,通信设备为第一通信设备时,通信接口用于向第二通信设备发送第一请求消息;并从第二通信设备接收网络性能分析信息。当该通信设备为第二通信设备时,通信接口用于从第一通信设备接收第一请求消息;并向第一通信设备发送网络性能分析信息。网络性能分析信息包括M个候选设备对应的网络性能分析信息,M为正整数。一个候选设备对应的网络性能分析信息包括以下至少一种信息:一个候选设备的无线接入制式信息;一个候选设备可参与联邦学习的时间信息;一个候选设备的所处位置信息;一个候选设备存在网络覆盖的时间段信息;在感兴趣时间内,一个候选设备存在网络覆盖的时间段占感兴趣时间的比例信息;一个候选设备的网络信号质量信息。
第七方面,提供了一种可读存储介质,所述可读存储介质上存储程序或指令,所述程序或指令被处理器执行时实现如第一方面或第二方面所述的设备确定方法的步骤。
第八方面,提供了一种芯片,所述芯片包括处理器和通信接口,所述通信接口和所述处理器耦合,所述处理器用于运行程序或指令,实现如第一方面或第二方面所述的设备确定方法的步骤。
第九方面,提供了一种计算机程序/程序产品,所述计算机程序/程序产品被存储在存储介质中,所述计算机程序/程序产品被至少一个处理器执行以实现如第一方面或第二方面所述的设备确定方法的步骤。
在本申请实施例中,第一通信设备向第二通信设备发送第一请求消息,第一请求消息用于请求获取网络性能分析信息;第一通信设备从第二通信设备接收该网络性能分析信息, 网络性能分析信息包括M个候选设备对应的网络性能,M为正整数。其中,一个候选设备对应的网络性能分析信息包括以下至少一种信息:该一个候选设备的无线接入制式信息;该一个候选设备可参与联邦学习的时间信息;该一个候选设备的所处位置信息;该一个候选设备存在网络覆盖的时间段信息;在感兴趣时间内,该一个候选设备存在网络覆盖的时间段占感兴趣时间的比例信息;该一个候选设备的网络信号质量信息。通过该方案,由于设备的无线接入制式信息、可参与联邦学习的时间信息、所处位置信息、存在网络覆盖的时间段信息、存在网络覆盖的时间段占感兴趣时间的比例信息,以及网络信号质量信息均可以反映设备对应的网络性能,因此在第一通信设备接收到网络性能分析信息之后,第一通信设备可以确定该M个候选设备中的每个候选设备对应的网络性能,从而第一通信设备可以将符合联邦学习的网络性能要求的候选设备,确定为参与联邦学习的设备,即第一通信设备可以选择合适的设备参与联邦学习。
附图说明
图1是本申请实施例提供的设备确定方法的流程示意图;
图2是本申请实施例提供的设备确定方法的示意图之一;
图3是本申请实施例提供的设备确定方法的示意图之二;
图4是本申请实施例提供的设备确定装置的结构示意图之一;
图5是本申请实施例提供的设备确定装置的结构示意图之二;
图6是本申请实施例提供的通信设备的结构示意图;
图7是本申请实施例提供的通信设备的硬件示意图。
具体实施方式
下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行清楚描述,显然,所描述的实施例是本申请一部分实施例,而不是全部的实施例。基于本申请中的实施例,本领域普通技术人员所获得的所有其他实施例,都属于本申请保护的范围。
本申请的说明书和权利要求书中的术语“第一”、“第二”等是用于区别类似的对象,而不用于描述特定的顺序或先后次序。应该理解这样使用的术语在适当情况下可以互换,以便本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施,且“第一”、“第二”所区别的对象通常为一类,并不限定对象的个数,例如第一通信设备可以是一个,也可以是多个。此外,说明书以及权利要求中“和/或”表示所连接对象的至少其中之一,字符“/”一般表示前后关联对象是一种“或”的关系。
值得指出的是,本申请实施例所描述的技术不限于长期演进型(Long Term Evolution,LTE)/LTE的演进(LTE-Advanced,LTE-A)系统,还可用于其他无线通信系统,诸如码分多址(Code Division Multiple Access,CDMA)、时分多址(Time Division Multiple Access,TDMA)、频分多址(Frequency Division Multiple Access,FDMA)、正交频分多址(Orthogonal Frequency Division Multiple Access,OFDMA)、单载波频分多址(Single-carrier Frequency Division Multiple Access,SC-FDMA)和其他系统。本申请实施例中的术语“系统”和“网络”常被可互换地使用,所描述的技术既可用于以上提及的系统和无线电技术,也可用于其他系统和无线电技术。以下描述出于示例目的描述了新空口(New Radio,NR)系统,并且在以下大部分描述中使用NR术语,但是这些技术也可应用于NR系统应用以外的应用,如第6代(6-th Generation,6G)通信系统。
本申请实施例中提及的通信设备(例如第一通信设备、第二通信设备、第三通信设备、第四通信设备和第五通信设备等)可以为核心网设备,也可以称为网元,或网络节点。其中,核心网设备可以包含但不限于如下至少一项:核心网节点、核心网功能、应用功能(Application Function,AF)、数据网络分析功能(Network Data Analytics Function,NWDAF)、统一数据管理(Unified Data Management,UDM)、网络开放功能(Network Exposure Function,NEF)、本地NEF(Local NEF,或L-NEF)、操作管理和维护(Operation Administration and Maintenance,OAM)、用户平面功能(User Plane Function,UPF)、会话管理功能(Session Management Function,SMF)、数据收集应用功能(Data Collection-Application Function,DC-AF)、移动管理实体(Mobility Management Entity,MME)、接入移动管理功能(Access andMobility Management Function,AMF)、用户平面功能(User Plane Function,UPF)、策略控制功能(Policy Control Function,PCF)、策略与计费规则功能单元(Policy and Charging Rules Function,PCRF)、边缘应用服务发现功能(EdgeApplication Server Discovery Function,EASDF)、统一数据仓储(Unified Data Repository,UDR)、归属用户服务器(Home Subscriber Server,HSS)、集中式网络配置(Centralized network configuration,CNC)、网络存储功能(Network Repository Function,NRF),绑定支持功能(Binding Support Function,BSF)等。需要说明的是,在本申请实施例中仅以NR系统中的核心网设备为例进行介绍,并不限定核心网设备的具体类型。
本申请实施例中的候选设备可以包括终端(也可以称为终端设备或用户设备(User Equipment,UE),或者其他任意可能的设备。其中,终端可以是手机、平板电脑(Tablet Personal Computer)、膝上型电脑(Laptop Computer)或称为笔记本电脑、个人数字助理(Personal Digital Assistant,PDA)、掌上电脑、上网本、超级移动个人计算机(Ultra-Mobile Personal Computer,UMPC)、移动上网装置(Mobile Internet Device,MID)、增强现实(Augmented Reality,AR)/虚拟现实(Virtual Reality,VR)设备、机器人、可穿戴式设备(Wearable Device)、车载设备(VUE)、行人终端(PUE)、智能家居(具有无线通信功能的家居设备,如冰箱、电视、洗衣机或者家具等)、游戏机、个人计算机(Personal Computer,PC)、柜员机或者自助机等终端侧设备,可穿戴式设备包括:智能手表、智能手环、智能耳机、智能眼镜、智能首饰(智能手镯、智能手链、智能戒指、智能项链、智能脚镯、智能脚链等)、智能腕带、智能服装等。需要说明的是,在本申请实施例并不限定终端的具体类型。
下面结合附图,通过一些实施例及其应用场景对本申请实施例提供的设备确定方法进行详细地说明。
如图1所示,本申请实施例提供一种设备确定方法,该方法可以包括下述的步骤201-步骤204。
步骤201、第一通信设备向第二通信设备发送第一请求消息。
步骤202、第二通信设备从第一通信设备接收第一请求消息。
其中,上述第一请求消息可以用于请求获取网络性能分析信息。
步骤203、第二通信设备向第一通信设备发送网络性能分析信息。
步骤204、第一通信设备从第二通信设备接收网络性能分析信息。
其中,网络性能分析信息可以包括M个候选设备对应的网络性能分析信息,M为正整数。一个候选设备对应的网络性能分析信息可以包括以下至少一种信息:
a)该一个候选设备的无线接入制式信息;
b)该一个候选设备可参与联邦学习的时间信息;
c)该一个候选设备的所处位置信息;
d)该一个候选设备存在网络覆盖的时间段信息;
e)在感兴趣时间内,该一个候选设备存在网络覆盖的时间段占感兴趣时间的比例信息;
f)该一个候选设备的网络信号质量信息。
本申请实施例中,在第二通信设备接收到上述第一请求消息之后,第二通信设备可以向第一通信设备发送上述M个候选设备对应的网络性能分析信息,从而第一通信设备可以获取该M个候选设备中的每个候选设备的网络性能,进而可以将符合联邦学习的网络性能要求的候选设备,确定为参与联邦学习的设备,即第一通信设备可以选择合适的候选设备进行联邦学习。
本申请实施例中,由于网络性能分析信息可以指示M个候选设备对应的网络性能,因此在第一通信设备接收到该网络性能分析信息之后,第一通信设备可以获取M个候选设备中的每个候选设备对应的网络性能,从而第一通信设备可以将符合联邦学习的网络性能要求的候选设备,确定为参与联邦学习的设备。
本申请实施例中,第一通信设备可以包括AF或其他任意可能的服务消费者实体;第二通信设备可以包括NWDAF;候选设备可以包括UE或者其他任意可能的设备。具体可以根据实际使用需求确定,本申请实施例对此不作限定。
本申请实施例中,无线接入制式可以为非第三代合作伙伴计划(non third generation partnership project,non 3GPP)的无线接入制式,例如无线局域网(wireless local area networks,WLAN),也可以为3GPP的无线接入指示,例如第四代通讯技术(fourth generation,4G)演进的UMTS地面无线接入网络(evolved universal terrestrial radio access network,EUTRAN or E-UTRAN),或第五代通讯技术(fifth generation,5G)NR等。
示例性地,对于上述a),一个候选设备的无线接入制式信息可以指示该候选设备的无线接入制式为non-3GPP的WLAN。
本申请实施例中,对于上述b),一个候选设备可参与联邦学习的时间信息可以指示该候选设备可参与联邦学习的时间,例如每天的00:00-04:00。
本申请实施例中,对于上述c),一个候选设备的所处位置信息可以指示该候选设备所处的区域、小区(cell)或跟踪区域(tracking area,TA)。
本申请实施例中,上述感兴趣时间可以为第一通信设备感兴趣的时间,例如第一通信设备计划进行联邦学习的时间。例如,第一通信设备计划进行联邦学习的时间为2020年03月15日的01:00-03:00。
对于上述d),一个候选设备存在网络覆盖的时间段信息可以指示该候选设备存在网络覆盖的时长或时间段。对于上述e),在感兴趣时间内,一个候选设备存在网络覆盖的时间段占感兴趣时间的比例信息(以下简称为网络覆盖时间比例信息)可以指示该候选设备在感兴趣时间内,该候选设备存在网络覆盖的时长与感兴趣时间对应的时长之间的比值。
示例性地,以候选设备为终端,无线接入制式为无线局域网(Wireless Local Area Networks,WLAN)为例,假设感兴趣时间为8:00-11:00的3个小时,该终端在这3个小时内的2个小时有无线保真(WIreless-Fidelity,Wi-Fi)覆盖,那么该终端存在Wi-Fi覆盖的 时间段占感兴趣时间的比例为2/3。
可选地,本申请实施例中,网络覆盖时间比例信息可以通过等级指示候选设备存在网络覆盖的时间段占感兴趣时间的比例,比如但不限于“高、中、低”等方式描述;或者,网络覆盖时间比例信息还可以通过小数、分数、或百分比等形式指示候选设备存在网络覆盖的时间段占感兴趣时间的比例。具体可以根据实际使用需求确定,本申请实施例不作限定。
本申请实施例中,网络信号质量信息用于指示设备的网络信号质量。网络信号质量可以包括信号质量、信号强度、信号稳定性中的至少一项。
其中,网络信号质量可以通过网络信号质量参数的平均值或峰值表示。
本申请实施例中,假设无线接入制式为WLAN,可以通过接收的信号强度指示(received signal strength indication,RSSI)和路径返回时间(round trip time,RTT)中的至少一项参数,表示网络信号质量。
可选地,本申请实施例中,上述第一请求消息可以包括上报粒度指示信息,该上报粒度指示信息可以用于指示以设备为粒度,上报候选设备对应的网络性能分析信息。例如上报粒度指示信息指示以UE(per UE)为粒度,上报候选UE对应的网络性能分析信息。如此,第一通信设备可以确定M个候选UE中的每个UE的网络性能,从而可以选择合适的UE参与联邦学习。
可选地,本申请实施例中,上述第一请求信息可以包括过滤信息,该过滤信息可以包括以下至少一项:
a)感兴趣区域(area of interest),也可以称为关注区域,例如一个或多个小区,或者一个或多个跟踪区(tracking area,TA)。
b)无线接入制式限定信息,该无线接入制式限定信息可以用于指示候选设备的无线接入制式。其中,对于无线接入制式的相关描述,可以参见上述实施例的相关描述。
c)感兴趣时间,感兴趣时间可可以为第一通信设备计划进行联邦学习的时间。例如,2020年03月15日的00:00-04:00,具体可以根据实际使用需求确定。
可选地,本申请实施例中,上述过滤信息还可以包括以下至少一项:
d)第二通信设备需要返回的候选设备的数量,即M的取值,例如M=500。
e)候选设备的网络信号质量限定信息,该网络信号质量限定信息可以用于指示要求的候选设备的网络信号质量阈值,该网络信号质量阈值可以为对候选设备的网络信号质量的最低需求。
示例性地,以信号稳定性(可以以网络信号强度保持在目标数值以上的时间比例表示)为例,当网络信号稳定性阈值为90%时,则表示要求候选设备在感兴趣时间内的90%及以上的时间里的信号强度可以达到目标数值。
f)算法限定信息,算法限定信息可以用于指示要求的候选设备支持的关于机器学习等人工智能(artificial intelligence,AI)数据分析任务相关的算法,例如深度学习,线性回归等。
g)模型的训练精度限定信息,模型的训练精度限定信息可以用于指示要求的候选设备参与联邦学习时可使用的模型可达到的训练精度,即该可使用的模型在训练完成后,可以达到的模型准确度。即该模型在训练完成后,正确预测(判断)的数量占预测总数的比例, 如准确率为90%。
h)模型的训练速度限定信息,该模型的训练速度限定信息可以用于指示要求的候选设备将参与联邦学习时可使用的模型,训练至第一训练精度(例如80%的正确率)所需要的训练时间。具体可以为候选设备在本地对该模型进行训练时,使该模型达到第一训练精度时所需要的训练时间。所需要的训练时间越长,训练速度越慢;所需要的训练时间越短,训练速度越快。
i)联邦学习的存储空间限定信息,该存储空间限定信息用于指示要求的候选设备预留的用于联邦学习的模型、数据等信息的存储空间大小,例如10兆比特(MB)。
可选地,本申请实施例中,上述第一请求消息还可以包括网络性能的分析标识(analytic identifier,analytic ID),该分析标识可以用于指示该第一请求消息对应的任务,比如此次任务为获取符合过滤信息的要求的候选设备的网络性能。示例性地,该网络性能分析标识可以为WLAN性能(performance)或者NRperformance。
可选地,本申请实施例中,第一请求消息还可以包括上报限定信息,该上报限定信息可以以下至少一项:
A)候选设备的排序信息,排序信息用于指示第二通信设备将候选设备按照某一参数/尺度升序或降序输出。假设按照信号强度降序输出,那么当第二通信设备返回结果(即向第一通信设备发送网络性能分析信息)时,可以按照信号强度从小到大的顺序,排列候选设备。
B)候选设备的分组信息,分组信息用于指示第二通信设备将候选设备按照某一参数/因素(例如时间、位置等)分组。比如,第二通信设备可以将所有候选设备中的在白天的10点至12点进行联邦学习的候选设备分为一组。
C)在感兴趣时间内,候选设备存在网络覆盖的时间段占感兴趣时间的比例(即网络覆盖时间比例)。
对于网络覆盖时间比例的描述,可以参见上述实施例的相关描述,为避免重复,此处不再赘述。
D)网络性能分析信息的格式。
E)网络性能分析信息包含的内容中。
本申请实施例提供的设备确定方法,由于设备的无线接入制式信息、可参与联邦学习的时间信息、所处位置信息、存在网络覆盖的时间段信息、存在网络覆盖的时间段占感兴趣时间的比例信息,以及网络信号质量信息均可以反映设备对应的网络性能,因此在第一通信设备接收到网络性能分析信息之后,第一通信设备可以确定该M个候选设备中的每个候选设备对应的网络性能,从而第一通信设备可以将符合联邦学习的网络性能要求的候选设备,确定为参与联邦学习的设备,即第一通信设备可以选择合适的设备参与联邦学习。
可选地,在上述步骤203之前,本申请实施例提供的设备确定方法还可以包括下述的步骤205和步骤206。
步骤205、第一通信设备根据网络性能分析信息,从M个候选设备中确定参与联邦学习的N个设备,N为小于或等于M的正整数。
步骤206、第一通信设备与N个设备建立连接,并进行联邦学习。
本申请实施例中,在第一通信设备接收到网络性能分析信息之后,第一通信设备可以 从上述M个候选设备中确定参与联邦学习的N个设备,然后可以与该N个设备建立连接,并进行联邦学习,从而可以得到符合第一通信设备需求的联邦学习模型。
示例性地,假设第一通信设备在上述过滤信息中,限定了需要连接WLAN且信号强度需达到阈值的UE,且限定在2020年03月15日在A市范围内进行联邦学习。则上述M个候选UE为满足这些条件的UE。第一通信设备可以根据在2020年03月15日,UE时间重叠的数量进行选择,如在2020年03月15日的下午2点到3点有500个满足条件的UE可以参与联邦学习,且下午2点到3点为当天UE时间重叠数量最多的时间,那么第一通信设备可以将该500个UE作为参与联邦学习的设备。从而第一通信设备可以在2020年03月15日的下午2点到3点,与该500个UE建立连接,并进行联邦学习。又或者,第一通信设备可以选择网络信号强度最好的UE作为参与联邦学习的设备。
可选地,本申请实施例中,在上述步骤205之前,本申请实施例提供的设备确定方法还可以包括下述的步骤207和步骤208中的至少之一。
需要说明的是,本申请不限定步骤207和步骤208的具体执行顺序/时机,步骤207和步骤208可以在上述步骤201之前执行,也可以在步骤204之后执行,具体可以根据实际使用需求确定,本申请实施例不作限定。
步骤207、第一通信设备确定M个候选设备具备联邦学习意愿。
步骤208、第一通信设备确定M个候选设备具备联邦学习能力。
本申请实施例中,在第一通信设备根据网络性能分析信息,从M个候选设备中确定参与联邦学习的N个设备之前,第一通信设备可以先确定M个候选设备的是否具备联邦学习意愿和/或联邦学习能力,在确定M个候选设备具备联邦学习意愿和/或联邦学习能力的情况下,可以从该M个候选设备中确定参与联邦学习的N个设备。
可选地,本申请实施例中,上述步骤207可以通过下述的步骤207a和步骤207b实现。
步骤207a、第一通信设备从第三通信设备获取M个候选设备的联邦学习意愿信息。
步骤207b、第一通信设备根据M个候选设备的联邦学习意愿信息,确定M个候选设备具备联邦学习意愿。
本申请实施例中,在第一通信设备从第三通信设备获取上述M个候选设备的联邦学习意愿信息之后,第一通信设备可以根据该M个候选设备的联邦学习意愿信息,确定M个候选设备具备联邦学习意愿。
可选地,本申请实施例中,上述第一通信设备从第三通信设备获取Q个设备的联邦学习意愿信息,并从该Q个设备的联邦学习意愿信息中,筛选上述M个候选设备的联邦学习意愿信息。可以理解,Q个设备可以包括M个候选设备。
本申请实施例中,上述第三通信设备可以为UDM。
可选地,本申请实施例中,上述联邦学习意愿信息可以包括以下至少一项:
是否愿意参与联邦学习的指示信息;
参与联邦学习的条件信息。
可选地,本申请实施例中,上述参与联邦学习的条件信息可以包括以下至少一项:
参与联邦学习时的无线接入制式,例如non-3GPP的WLAN;
参与联邦学习的时间,即能够参与联邦学习的时间,比如凌晨2:00-5:00;
参与联邦学习时的所处位置,比如参与联邦学习时所处区域或所接入的小区。
可选地,本申请实施例中,上述步骤208可以通过下述的步骤208a和步骤208b实现。
步骤208a、第一通信设备从第三通信设备获取M个候选设备的联邦学习能力信息。
步骤208b、第一通信设备根据M个候选设备的联邦学习能力信息,确定M个候选设备具备联邦学习能力。
本申请实施例中,在第一通信设备从第三通信设备获取上述M个候选设备的联邦学习能力信息之后,第一通信设备可以根据该M个候选设备的联邦学习能力信息,确定M个候选设备具备联邦学习能力。
可选地,本申请实施例中,上述第一通信设备从第三通信设备获取S个设备的联邦学习意愿信息,并从该S个设备的联邦学习意愿信息中,筛选上述M个候选设备的联邦学习意愿信息。可以理解,S个设备可以包括M个候选设备。
可选地,本申请实施例中,上述联邦学习能力信息可以包括以下至少一项:
参与联邦学习时可使用的模型,例如使用特定网络架构的模型,如残差网络(Residual Networks,ResNet)、Inception-v3等。
参与联邦学习时可使用的算法,例如梯度下降等。
参与联邦学习时可达到的模型的训练精度,即在将该可使用的模型训练完成后,该可使用的模型所能达到的模型准确度,例如所能达到的最高准确度。即该模型在训练完成后,正确预测、判断的数量占总数的比例,如准确率为90%。
参与联邦学习时可达到的模型的训练速度,该训练速度用于指示将第参与联邦学习时可使用的模型训练至第一训练精度所需要的训练时间,即第一设备在本地训练该可使用的模型时,将该模型训练至第一训练精度(例如80%)所需要的训练时间(例如30分钟)。其中,训练时间越长,训练速度越慢;训练时间越短,训练速度越快。
参与联邦学习的存储空间大小,即预留的用于联邦学习的模型、数据等信息的存储空间大小,比如15MB。
可选地,在上述步骤207a或步骤208a之前,本申请实施例提供的设备确定方法还可以包括下述的步骤209。
步骤209、第一通信设备从第五通信设备获取第三通信设备的网络功能开放信息。
上述第五通信设备可以为NEF或者其它通信设备,具体可以根据实际使用需求确定。
第一通信设备可以向第五通信设备发送第二请求信息,以请求获取第三通信设备的网络功能的开放信息,从而可以与第三通信设备进行交互。例如,第一通信设备可以从上述第三通信设备获取M个候选设备的联邦学习意愿信息和/或M个候选设备的联邦学习能力信息。
可选地,本申请实施例中,在上述步骤203之前,本申请实施例提供的设备确定方法还可以包括下述的步骤210和步骤211。
步骤210、第二通信设备从第四通信设备获取M个候选设备的对应的网络性能数据。
步骤211、第二通信设备对M个候选设备对应的网络性能数据进行分析,得到该M个候选设备对应的网络性能分析信息。
本申请实施例中,第二通信设备可以从第四通信设备获取上述M个候选设备对应的网络性能数据,然后对该M个候选设备对应网络性能数据进行分析,从而可以得到该M个候选设备对应的网络性能分析信息。
可选地,本申请实施例中,上述第四通信设备可以包括SMF、OAM、UDM和DC-AF等网元中的至少一项。
可选地,本申请实施例中,上述步骤210可以通过下述的步骤210a和步骤210b中的至少一项实现。
步骤210a、第二通信设备从SMF获取所述M个候选设备对应的:无线接入制式信息、网络覆盖时间信息、会话在网络中的时间信息中的至少一项;
步骤210b、第二通信设备从网络管理设备获取所述M个候选设备对应的:网络标识信息、网络信号质量信息中的至少一项。
示例性地,以第二通信设备为NWDAF为例,NWDAF可以从OAM获取M个候选设备对应的网络信号质量信息,例如设备连接WLAN的信号质量信息(比如RTT,RSSI等),并从OAM获取M个候选设备对应的网络标识信息,例如服务集标识(Service Set Identifier,SSID)等;从SMF获取M个候选设备对应的无线接入制式信息,例如WLAN、5G NR,或4G EUTRAN等,并从SMF获取M个候选设备对应的网络覆盖时间信息,例如WLAN的覆盖时间;从UDM或者从DCAF获取M个候选设备支持的算法信息、可达到的模型的训练精度信息等;并从UPF获取M个候选设备对应的流量信息等。
本申请实施例中,在第二通信设备得到上述M个候选设备对应的网络性能数据之后,第二通信设备可以对该M个候选设备的网络性能数据进行分析,从而可以得到该M个候选设备的网络性能分析结果,进而可以根据该M个候选设备的网络性能分析结果,生成该M个候选设备对应的网络性能分析信息。
下面结合表1,以设备的无线接入方式为WLAN为例,对设备的网络性能分析结果进行示例性的说明。
表1

可选地,本申请实施例中,在上述步骤203之前,本申请实施例提供的设备确定方法还可以包括下述的步骤212。
步骤212、第二通信设备根据第一请求消息包括的过滤信息,确定M个候选设备。
其中,所述M个候选设备中的每个候选设备满足以下至少一项条件:
位于感兴趣区域内;
无线接入制式为无线接入制式限定信息指示的无线接入制式;
在感兴趣时间内,存在网络覆盖。
可选地,本申请实施例中,上述M个候选设备中的每个候选设备还可以满足以下至少一项条件:
网络信号质量大于或等于网络信号质量限定信息指示的网络信号质量;
支持的算法为算法限定信息指示的算法;
参与联邦学习时可达到的模型的训练精度,大于或等于模型的训练精度限定信息指示的训练精度;
参与联邦学习时可达到的模型的训练速度,大于或等于模型的训练速度限定信息指示的训练速度;
参与联邦学习的存储空间大小,大于或等于联邦学习的存储空间限定信息指示的存储空间大小。
示例性地,假设上述模型的训练精度限定信息指示的训练精度为85%,那么当上述K个设备中的某个设备与联邦学习时可达到的模型的训练精度为93%,那么可以将该设备可以确定为候选设备。
可选地,本申请实施例中,在上述步骤203之前,本申请实施例提供的设备确定方法还可以包括下述的步骤213和/或步骤214。
步骤213、第二通信设备确定M个候选设备具备联邦学习意愿。
步骤214、第二通信设备确定M个候选设备具备联邦学习能力。
本申请实施例中,在第二通信设备向第一通信设备发送网络性能分析信息之前,第一通信设备可以先确定M个候选设备的是否具备联邦学习意愿和/或联邦学习能力,在确定M个候选设备具备联邦学习意愿和/或联邦学习能力的情况下,可以向第一通信设备发送该M个候选设备对应的网络性能分析信息。
可选地,本申请实施例中,上述步骤213可以通过下述的步骤213a和步骤213b实现。
步骤213a、第二通信设备从第三通信设备获取M个候选设备的联邦学习意愿信息。
步骤213b、第二通信设备根据M个候选设备的联邦学习意愿信息,确定M个候选设备具备联邦学习意愿。
本申请实施例中,在第二通信设备从第三通信设备获取上述M个候选设备的联邦学习意愿信息之后,第一通信设备可以根据该M个候选设备的联邦学习意愿信息,确定M个候选设备具备联邦学习意愿,从而可以将具备联邦学习意愿的M个候选设备对应的网络性能分析信息,发送给第一通信设备。如此,第一通信设备可以直接从该M个候选设备中选择 相应的设备参与联邦学习。
可选地,本申请实施例中,上述第二通信设备从第三通信设备获取W个设备的联邦学习意愿信息,并从该W个设备的联邦学习意愿信息中,筛选上述M个候选设备的联邦学习意愿信息。可以理解,W个设备可以包括M个候选设备。
本申请实施例中,上述第三通信设备可以为UDM。
需要说明的是,对于联邦学习意愿信息的描述,可以参与上述实施例中的相关描述,为避免重复,此处不再赘述。
可选地,本申请实施例中,上述步骤214可以通过下述的步骤214a和步骤214b实现。
步骤214a、第二通信设备从第三通信设备获取M个候选设备的联邦学习能力信息。
步骤214b、第二通信设备根据M个候选设备的联邦学习能力信息,确定M个候选设备具备联邦学习能力。
本申请实施例中,在第二通信设备从第三通信设备获取上述M个候选设备的联邦学习能力信息之后,第一通信设备可以根据该M个候选设备的联邦学习能力信息,确定M个候选设备具备联邦学习能力,从而可以将具备联邦学习能力的M个候选设备对应的网络性能分析信息,发送给第一通信设备。如此,第一通信设备可以直接从该M个候选设备中选择相应的设备参与联邦学习。
可选地,本申请实施例中,上述第二通信设备从第三通信设备获取P个设备的联邦学能力信息,并从该P个设备的联邦学习意愿能力中,筛选上述M个候选设备的联邦学习能力信息。可以理解,P个设备可以包括M个候选设备。
需要说明的是,对于联邦学习能力信息的描述,可以参与上述实施例中的相关描述,为避免重复,此处不再赘述。
可选地,在上述步骤213a或步骤214a之前,本申请实施例提供的设备确定方法还可以包括下述的步骤215。
步骤215、第二通信设备从第五通信设备获取第三通信设备的网络功能开放信息。
上述第五通信设备可以为NEF或者其它通信设备,具体可以根据实际使用需求确定。
第二通信设备可以向第五通信设备发送第二请求信息,以请求获取第三通信设备的网络功能的开放信息,从而可以与第三通信设备进行交互。例如,第二通信设备可以从上述第三通信设备获取M个候选设备的联邦学习意愿信息和/或M个候选设备的联邦学习能力信息。
下面再结合图2和图3,对本申请实施例提供的设备确定方法进行示例性地说明。
如图2所示,步骤0a:AF等服务消费者向NEF发送请求,以获取关于UDM/NRF/DCAF等通信设备的网络功能开放信息,为了之后从UDM等通信设备获取候选设备的联邦学习意愿信息和/或联邦学习能力信息,进而确定设备是否具备联邦学习能力和/联邦学习意愿。
步骤0b:AF等服务消费者向UDM/NRF/DC-AF等能力存储网元请求获取联邦学习意愿信息和/或联邦学习能力信息。
如图3所示,步骤1:AF等服务消费者向NWDAF发送第一请求消息(可以使用Nnwdaf_AnalyticsInfo或Nnwdaf_AnalyticsSubscription),请求获取网络性能分析信息。
步骤2:NWDAF根据第一请求消息的任务描述和限定条件,从SMF、OAM、UDM等数据提供者获取关于UE的无线连接制式、信号质量等网络性能数据。其中,步骤2可以包 括步骤2a、步骤2b和步骤2c。
步骤3:NWDAF使用所获取到的网络性能数据进行分析,得到UE粒度的网络性能分析结果,从而得到网络性能分析信息。
步骤4:NWDAF根据步骤1中的第一请求消息的描述信息,返回任务响应消息,即向AF等等服务消费者发送网络性能分析信息。NWDAF可以根据步骤1所使用的Nnwdaf_AnalyticsInfo或Nnwdaf_AnalyticsSubscription进行对应的响应。
步骤5:AF等服务消费者根据步骤4中返回的响应消息,确定参与联邦学习的UE(s)。
步骤6:AF等服务消费者根据步骤5中确定的参与联邦学习的UE(s)的标识信息,与UE(s)建立连接,并进行联邦学习。
本申请实施例提供的设备确定方法,执行主体还可以为设备确定装置。本申请实施例中以设备确定装置执行设备确定方法为例,说明本申请实施例提供的设备确定装置。
如图4所示,本申请实施例提供一种设备确定装置300,该联邦学习的设备获取装置300包括发送模块301和接收模块302。发送模块301,用于向第二通信设备发送第一请求消息,第一请求消息用于请求获取网络性能分析信息;接收模块302,用于从第二通信设备接收网络性能分析信息,网络性能分析信息包括M个候选设备对应的网络性能分析信息,M为正整数。其中,一个候选设备对应的网络性能分析信息包括以下至少一种信息:一个候选设备的无线接入制式信息;一个候选设备可参与联邦学习的时间信息;一个候选设备的所处位置信息;一个候选设备存在网络覆盖的时间段信息;在感兴趣时间内,一个候选设备存在网络覆盖的时间段占感兴趣时间的比例信息;一个候选设备的网络信号质量信息。
可选地,设备确定装置还包括确定模块和执行模块;确定模块,用于根据网络性能分析信息,从M个候选设备中确定参与联邦学习的N个设备,N为小于或等于M的正整数;执行模块,用于与N个设备建立连接,并进行联邦学习。
可选地,第一请求消息包括上报粒度指示信息,上报粒度指示信息用于指示以设备为粒度,上报候选设备对应的网络性能。
可选地,第一请求消息包括过滤信息,过滤信息包括以下至少一项:
感兴趣区域;
无线接入制式限定信息;
感兴趣时间。
可选地,确定模块,还用于确定M个候选设备具备联邦学习意愿;和/或,确定模块,还用于确定M个候选设备具备联邦学习能力。
可选地,确定模块包括获取子模块和确定子模块;获取子模块,用于从第三通信设备获取M个候选设备的联邦学习意愿信息;确定子模块,用于根据M个候选设备的联邦学习意愿信息,确定M个候选设备具备联邦学习意愿。
可选地,确定模块包括获取子模块和确定子模块;获取子模块,用于从第三通信设备获取M个候选设备的联邦学习能力信息;确定子模块,用于根据M个候选设备的联邦学习能力信息,确定M个候选设备具备联邦学习能力。
可选地,联邦学习意愿信息包括以下至少一项:
是否愿意参与联邦学习的指示信息;
参与联邦学习的条件信息。
可选地,参与联邦学习的条件信息包括以下至少一项:
参与联邦学习时的无线接入制式;
参与联邦学习的时间;
参与联邦学习时的所处位置。
可选地,联邦学习能力信息包括以下至少一项:
参与联邦学习时可使用的模型;
参与联邦学习时可使用的算法;
参与联邦学习时可达到的模型的训练精度;
参与联邦学习时可达到的模型的训练速度,训练速度用于指示将可使用的模型训练至第一训练精度所需要的训练时间;
参与联邦学习的存储空间大小。
可选地,上述第二通信设备包括NWDAF。
本申请实施例提供一种设备确定装置,由于设备的无线接入制式信息、可参与联邦学习的时间信息、所处位置信息、存在网络覆盖的时间段信息、存在网络覆盖的时间段占感兴趣时间的比例信息,以及网络信号质量信息均可以反映设备对应的网络性能,因此在接收到网络性能分析信息之后,设备确定装置可以确定该M个候选设备中的每个候选设备对应的网络性能,从而可以将符合联邦学习的网络性能要求的候选设备,确定为参与联邦学习的设备,即设备确定装置可以选择合适的设备参与联邦学习。
如图5所示,本申请实施例提供一种设备确定装置400,该设备确定装置400包括接收单元401和发送单元402。接收单元401,可以用于从第一通信设备接收第一请求消息,第一请求消息用于请求获取网络性能分析信息;发送单元,用于向第一通信设备发送网络性能分析信息,网络性能分析信息包括M个候选设备对应的网络性能分析信息,M为正整数。其中,一个候选设备对应的网络性能分析信息包括以下至少一种信息:该一个候选设备的无线接入制式信息;该一个候选设备可参与联邦学习的时间信息;该一个候选设备的所处位置信息;该一个候选设备存在网络覆盖的时间段信息;在感兴趣时间内,该一个候选设备存在网络覆盖的时间段占感兴趣时间的比例信息;该一个候选设备的网络信号质量信息。
可选地,第一请求消息包括上报粒度指示信息,上报粒度指示信息用于指示以设备为粒度,上报候选设备对应的网络性能。
可选地,第一请求消息包括过滤信息,过滤信息包括以下至少一项:
感兴趣区域;
无线接入制式限定信息;
感兴趣时间。
可选地,设备确定装置还包括获取单元和分析单元。获取单元,用于从第四通信设备获取M个候选设备的对应的网络性能数据;分析单元,用于对M个候选设备对应的网络性能数据进行分析,得到所述M个候选设备对应的网络性能分析信息。
可选地,获取单元包括第一获取子单元和第二获取子单元;第一获取子单元,用于从会话管理功能网元SMF获取所述M个候选设备对应的:无线接入制式信息、网络覆盖时间信息、会话在网络中的时间信息中的至少一项;所述第二获取子单元,用于从网络管理设备获取所述M个候选设备对应的:网络标识信息、网络信号质量信息中的至少一项。
可选地,设备确定装置还包括确定单元;所述确定单元,用于根据所述第一请求消息包括的过滤信息,确定所述M个候选设备,其中,所述M个候选设备中的每个候选设备满足以下至少一项条件:
位于感兴趣区域内;
无线接入制式为无线接入制式限定信息指示的无线接入制式的无线接入制式;
在感兴趣时间内,存在网络覆盖。
可选地,设备确定装置还包括确定单元;确定单元,用于确定M个候选设备具备联邦学习意愿;和/或,确定单元,用于确定M个候选设备具备联邦学习能力。
可选地,确定单元包括获取子单元和确定子单元;获取子单元,用于从第三通信设备获取M个候选设备的联邦学习意愿信息;确定子单元,用于根据M个候选设备的联邦学习意愿信息,确定M个候选设备具备联邦学习意愿。
可选地,确定单元包括获取子单元和确定子单元;获取子单元,用于从第三通信设备获取M个候选设备的联邦学习能力信息;确定子单元,用于根据M个候选设备的联邦学习能力信息,确定M个候选设备具备联邦学习能力。
可选地,联邦学习意愿信息包括以下至少一项:
是否愿意参与联邦学习的指示信息;
参与联邦学习的条件信息。
可选地,参与联邦学习的条件信息包括以下至少一项:
参与联邦学习时的无线接入制式;
参与联邦学习的时间;
参与联邦学习时的所处位置。
可选地,联邦学习能力信息包括以下至少一项:
参与联邦学习时可使用的模型;
参与联邦学习时可使用的算法;
参与联邦学习时可达到的模型的训练精度;
参与联邦学习时可达到的模型的训练速度,训练速度用于指示将可使用的模型训练至第一训练精度时所需要的训练时间;
参与联邦学习的存储空间大小。
本申请实施例提供一种设备确定装置由于设备的无线接入制式信息、可参与联邦学习的时间信息、所处位置信息、存在网络覆盖的时间段信息、存在网络覆盖的时间段占感兴趣时间的比例信息,以及网络信号质量信息均可以反映设备对应的网络性能,因此在设备确定装置向第一通信设备发送网络性能分析信息之后,可以使得第一通信设备确定该M个候选设备中的每个候选设备对应的网络性能,从而可以使得第一通信设备将符合联邦学习的网络性能要求的候选设备,确定为参与联邦学习的设备,即可以使得第一通信设备能够选择合适的设备参与联邦学习。
本申请实施例中的设备确定装置可以是电子设备,例如具有操作系统的电子设备,也可以是电子设备中的部件,例如集成电路或芯片。该电子设备可以是终端,也可以为除终端之外的其他设备。示例性的,终端可以包括但不限于上述所列举的终端11的类型,其他设备可以为服务器、网络附属存储器(Network Attached Storage,NAS)等,本申请实施例 不作具体限定。
本申请实施例提供的设备确定装置能够实现上述方法实施例实现的各个过程,并达到相同的技术效果,为避免重复,这里不再赘述。
可选地,如图6所示,本申请实施例还提供一种通信设备500,包括处理器501和存储器502,存储器502上存储有可在处理器501上运行的程序或指令,例如,该通信设备500为第一通信设备时,该程序或指令被处理器501执行时实现上述设备确定方法实施例的各个步骤,且能达到相同的技术效果。该通信设备500为第二通信设备时,该程序或指令被处理器501执行时实现上述设备确定方法实施例的各个步骤,且能达到相同的技术效果,为避免重复,这里不再赘述。
本申请实施例还提供一种通信设备,包括处理器和通信接口,当该通信设备为第一通信设备时,通信接口用于向第二通信设备发送第一请求消息;并从第二通信设备接收网络性能分析信息。当该通信设备为第二通信设备时,通信接口用于从第一通信设备接收第一请求消息;并向第一通信设备发送网络性能分析信息。网络性能分析信息包括M个候选设备对应的网络性能分析信息,M为正整数。一个候选设备对应的网络性能分析信息包括以下至少一种信息:一个候选设备的无线接入制式信息;一个候选设备可参与联邦学习的时间信息;一个候选设备的所处位置信息;一个候选设备存在网络覆盖的时间段信息;在感兴趣时间内,一个候选设备存在网络覆盖的时间段占感兴趣时间的比例信息;一个候选设备的网络信号质量信息。该通信设备实施例与上述第一通信设备或第二通信设备方法实施例对应,上述方法实施例的各个实施过程和实现方式均可适用于该通信设备实施例中,且能达到相同的技术效果。
具体地,本申请实施例还提供了一种通信设备。如图7所示,该通信设备600包括:处理器601、网络接口602和存储器603。其中,网络接口602例如为通用公共无线接口(common public radio interface,CPRI)。
本发明实施例的通信设备600还包括:存储在存储器603上并可在处理器y01上运行的指令或程序,处理器601调用存储器y03中的指令或程序执行上述设备确定装置中的各模块执行的方法,并达到相同的技术效果,为避免重复,故不在此赘述。
本申请实施例还提供一种可读存储介质,可读存储介质上存储有程序或指令,该程序或指令被处理器执行时实现上述设备确定方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。
其中,处理器为上述实施例中的终端中的处理器。可读存储介质,包括计算机可读存储介质,如计算机只读存储器ROM、随机存取存储器RAM、磁碟或者光盘等。
本申请实施例另提供了一种芯片,芯片包括处理器和通信接口,通信接口和处理器耦合,处理器用于运行程序或指令,实现上述设备确定方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。
应理解,本申请实施例提到的芯片还可以称为系统级芯片,系统芯片,芯片系统或片上系统芯片等。
本申请实施例另提供了一种计算机程序/程序产品,计算机程序/程序产品被存储在存储介质中,计算机程序/程序产品被至少一个处理器执行以实现上述设备确定方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。
需要说明的是,在本文中,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。此外,需要指出的是,本申请实施方式中的方法和装置的范围不限按示出或讨论的顺序来执行功能,还可包括根据所涉及的功能按基本同时的方式或按相反的顺序来执行功能,例如,可以按不同于所描述的次序来执行所描述的方法,并且还可以添加、省去、或组合各种步骤。另外,参照某些示例所描述的特征可在其他示例中被组合。
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件,但很多情况下前者是更佳的实施方式。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以计算机软件产品的形式体现出来,该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中,包括若干指令用以使得一台终端(可以是手机,计算机,服务器,空调器,或者网络设备等)执行本申请各个实施例的方法。
上面结合附图对本申请的实施例进行了描述,但是本申请并不局限于上述的具体实施方式,上述的具体实施方式仅仅是示意性的,而不是限制性的,本领域的普通技术人员在本申请的启示下,在不脱离本申请宗旨和权利要求所保护的范围情况下,还可做出很多形式,均属于本申请的保护之内。

Claims (48)

  1. 一种设备确定方法,所述方法包括:
    第一通信设备向第二通信设备发送第一请求消息,所述第一请求消息用于请求获取网络性能分析信息;
    所述第一通信设备从所述第二通信设备接收所述网络性能分析信息,所述网络性能分析信息包括M个候选设备对应的网络性能分析信息,M为正整数;
    其中,一个候选设备对应的网络性能分析信息包括以下至少一种信息:
    所述一个候选设备的无线接入制式信息;
    所述一个候选设备可参与联邦学习的时间信息;
    所述一个候选设备的所处位置信息;
    所述一个候选设备存在网络覆盖的时间段信息;
    在感兴趣时间内,所述一个候选设备存在网络覆盖的时间段占所述感兴趣时间的比例信息;
    所述一个候选设备的网络信号质量信息。
  2. 根据权利要求1所述的方法,其中,所述第一通信设备从所述第二通信设备接收所述网络性能分析信息之后,所述方法还包括:
    所述第一通信设备根据所述网络性能分析信息,从所述M个候选设备中确定参与所述联邦学习的N个设备,N为小于或等于M的正整数;
    所述第一通信设备与所述N个设备建立连接,并进行联邦学习。
  3. 根据权利要求1所述的方法,其中,所述第一请求消息包括上报粒度指示信息,所述上报粒度指示信息用于指示以设备为粒度,上报候选设备对应的网络性能分析信息。
  4. 根据权利要求1所述的方法,其中,所述第一请求消息包括过滤信息,所述过滤信息包括以下至少一项:
    感兴趣区域;
    无线接入制式限定信息;
    所述感兴趣时间。
  5. 根据权利要求2所述的方法,其中,在所述第一通信设备根据所述网络性能分析信息,从所述M个候选设备中确定参与所述联邦学习的N个设备之前,所述方法还包括:
    所述第一通信设备确定所述M个候选设备具备联邦学习意愿;和/或,
    所述第一通信设备确定所述M个候选设备具备联邦学习能力。
  6. 根据权利要求5所述的方法,其中,所述第一通信设备确定所述M个候选设备具备联邦学习意愿,包括:
    所述第一通信设备从第三通信设备获取所述M个候选设备的联邦学习意愿信息;
    所述第一通信设备根据所述M个候选设备的联邦学习意愿信息,确定所述M个候选设备具备联邦学习意愿。
  7. 根据权利要求5所述的方法,其中,所述第一通信设备确定所述M个候选设备具备联邦学习能力,包括:
    所述第一通信设备从第三通信设备获取所述M个候选设备的联邦学习能力信息;
    所述第一通信设备根据所述M个候选设备的联邦学习能力信息,确定所述M个候选设 备具备联邦学习能力。
  8. 根据权利要求6所述的方法,其中,所述联邦学习意愿信息包括以下至少一项:
    是否愿意参与联邦学习的指示信息;
    参与联邦学习的条件信息。
  9. 根据权利要求8所述的方法,其中,所述参与联邦学习的条件信息包括以下至少一项:
    参与联邦学习时的无线接入制式;
    参与联邦学习的时间;
    参与联邦学习时的所处位置。
  10. 根据权利要求7所述的方法,其中,所述联邦学习能力信息包括以下至少一项:
    参与联邦学习时可使用的模型;
    参与联邦学习时可使用的算法;
    参与联邦学习时可达到的模型的训练精度;
    参与联邦学习时可达到的模型的训练速度,所述训练速度用于指示将所述可使用的模型训练至第一训练精度所需要的训练时间;
    参与联邦学习的存储空间大小。
  11. 根据权利要求1所述的方法,其中,所述第一通信设备包括应用功能AF,所述第二通信设备包括网络数据分析功能NWDAF。
  12. 一种设备确定方法,所述方法包括:
    第二通信设备从第一通信设备接收第一请求消息,所述第一请求消息用于请求获取网络性能分析信息;
    所述第二通信设备向所述第一通信设备发送所述网络性能分析信息,所述网络性能分析信息包括M个候选设备对应的网络性能分析信息,M为正整数;
    其中,一个候选设备对应的网络性能分析信息包括以下至少一种信息:
    所述一个候选设备的无线接入制式信息;
    所述一个候选设备可参与联邦学习的时间信息;
    所述一个候选设备的所处位置信息;
    所述一个候选设备存在网络覆盖的时间段信息;
    在感兴趣时间内,所述一个候选设备存在网络覆盖的时间段占所述感兴趣时间的比例信息;
    所述一个候选设备的网络信号质量信息。
  13. 根据权利要求12所述的方法,其中,所述第一请求消息包括上报粒度指示信息,所述上报粒度指示信息用于指示以设备为粒度,上报候选设备对应的网络性能分析信息。
  14. 根据权利要求12所述的方法,其中,所述第一请求消息包括过滤信息,所述过滤信息包括以下至少一项:
    感兴趣区域;
    无线接入制式限定信息;
    所述感兴趣时间。
  15. 根据权利要求12至14中任意一项所述的方法,其中,所述第二通信设备向所述第 一通信设备发送所述网络性能分析信息之前,所述方法还包括:
    所述第二通信设备从第四通信设备获取所述M个候选设备对应的网络性能数据;
    所述第二通信设备对所述M个候选设备对应的网络性能数据进行分析,得到所述M个候选设备对应的网络性能分析信息。
  16. 根据权利要求15所述的方法,其中,所述第二通信设备从第四通信设备获取所述M个候选设备对应的网络性能数据,包括以下至少一项:
    所述第二通信设备从会话管理功能网元SMF获取所述M个候选设备对应的:无线接入制式信息、网络覆盖时间信息、会话在网络中的时间信息中的至少一项;
    所述第二通信设备从网络管理设备获取所述M个候选设备对应的:网络标识信息、网络信号质量信息中的至少一项。
  17. 根据权利要求12至14中任意一项所述的方法,其中,在所述第二通信设备向所述第一通信设备发送所述网络性能分析信息之前,所述方法还包括:
    所述第二通信设备根据所述第一请求消息包括的过滤信息,确定所述M个候选设备,其中,所述M个候选设备中的每个候选设备满足以下至少一项条件:
    位于所述感兴趣区域内;
    无线接入制式为所述无线接入制式限定信息指示的无线接入制式;
    在所述感兴趣时间内,存在网络覆盖。
  18. 根据权利要求12所述的方法,其中,所述第二通信设备向所述第一通信设备发送所述网络性能分析信息之前,所述方法还包括:
    所述第二通信设备确定所述M个候选设备具备联邦学习意愿;和/或,
    所述第二通信设备确定所述M个候选设备具备联邦学习能力。
  19. 根据权利要求18所述的方法,其中,所述第二通信设备确定所述M个候选设备具备联邦学习意愿,包括:
    所述第二通信设备从第三通信设备获取所述M个候选设备的联邦学习意愿信息;
    所述第二通信设备根据所述M个候选设备的联邦学习意愿信息,确定所述M个候选设备具备联邦学习意愿。
  20. 根据权利要求18所述的方法,其中,所述第一通信设备确定所述M个候选设备具备联邦学习能力,包括:
    所述第二通信设备从第三通信设备获取所述M个候选设备的联邦学习能力信息;
    所述第二通信设备根据所述M个候选设备的联邦学习能力信息,确定所述M个候选设备具备联邦学习能力。
  21. 根据权利要求19所述的方法,其中,所述联邦学习意愿信息包括以下至少一项:
    是否愿意参与联邦学习的指示信息;
    参与联邦学习的条件信息。
  22. 根据权利要求20所述的方法,其中,所述参与联邦学习的条件信息包括以下至少一项:
    参与联邦学习时的无线接入制式;
    参与联邦学习的时间;
    参与联邦学习时的所处位置。
  23. 根据权利要求20所述的方法,其中,所述联邦学习能力信息包括以下至少一项:
    参与联邦学习时可使用的模型;
    参与联邦学习时可使用的算法;
    参与联邦学习时可达到的模型的训练精度;
    参与联邦学习时可达到的模型的训练速度,所述训练速度用于指示将所述可使用的模型训练至第一训练精度所需要的训练时间;
    参与联邦学习的存储空间大小。
  24. 根据权利要求12所述的方法,其特征在在于,所述第一通信设备包括应用功能AF,所述第二通信设备包括括网络数据分析功能NWDAF。
  25. 一种设备确定装置,包括:
    发送模块,用于向第二通信设备发送第一请求消息,所述第一请求消息用于请求获取网络性能分析信息;
    接收模块,用于从所述第二通信设备接收所述网络性能分析信息,所述网络性能分析信息包括M个候选设备对应的网络性能分析信息,M为正整数;
    其中,一个候选设备对应的网络性能分析信息包括以下至少一种信息:
    所述一个候选设备的无线接入制式信息;
    所述一个候选设备可参与联邦学习的时间信息;
    所述一个候选设备的所处位置信息;
    所述一个候选设备存在网络覆盖的时间段信息;
    在感兴趣时间内,所述一个候选设备存在网络覆盖的时间段占所述感兴趣时间的比例信息;
    所述一个候选设备的网络信号质量信息。
  26. 根据权利要求25所述的装置,其中,所述设备确定装置还包括确定模块和执行模块;
    所述确定模块,用于根据所述网络性能分析信息,从所述M个候选设备中确定参与所述联邦学习的N个设备,N为小于或等于M的正整数;
    所述执行模块,用于与所述N个设备建立连接,并进行联邦学习。
  27. 根据权利要求25所述的装置,其中,所述第一请求消息包括上报粒度指示信息,所述上报粒度指示信息用于指示以设备为粒度,上报候选设备对应的网络性能。
  28. 根据权利要求25所述的装置,其中,所述第一请求消息包括过滤信息,所述过滤信息包括以下至少一项:
    感兴趣区域;
    无线接入制式限定信息;
    所述感兴趣时间。
  29. 根据权利要求26所述的装置,其中,所述确定模块,还用于确定所述M个候选设备具备联邦学习意愿;和/或,
    所述确定模块,还用于确定所述M个候选设备具备联邦学习能力。
  30. 根据权利要求29所述的装置,其中,所述确定模块包括获取子模块和确定子模块;
    所述获取子模块,用于从第三通信设备获取所述M个候选设备的联邦学习意愿信息;
    所述确定子模块,用于根据所述M个候选设备的联邦学习意愿信息,确定所述M个候选设备具备联邦学习意愿。
  31. 根据权利要求29所述的装置,其中,所述确定模块包括获取子模块和确定子模块;
    所述获取子模块,用于从第三通信设备获取所述M个候选设备的联邦学习能力信息;
    所述确定子模块,用于根据所述M个候选设备的联邦学习能力信息,确定所述M个候选设备具备联邦学习能力。
  32. 根据权利要求30所述的装置,其中,所述联邦学习意愿信息包括以下至少一项:
    是否愿意参与联邦学习的指示信息;
    参与联邦学习的条件信息。
  33. 根据权利要求32所述的装置,其中,所述参与联邦学习的条件信息包括以下至少一项:
    参与联邦学习时的无线接入制式;
    参与联邦学习的时间;
    参与联邦学习时的所处位置。
  34. 根据权利要求31所述的装置,其中,所述联邦学习能力信息包括以下至少一项:
    参与联邦学习时可使用的模型;
    参与联邦学习时可使用的算法;
    参与联邦学习时可达到的模型的训练精度;
    参与联邦学习时可达到的模型的训练速度,所述训练速度用于指示将所述可使用的模型训练至第一训练精度所需要的训练时间;
    参与联邦学习的存储空间大小。
  35. 一种设备确定装置,包括:
    接收单元,用于从第一通信设备接收第一请求消息,所述第一请求消息用于请求获取网络性能分析信息;
    发送单元,用于向所述第一通信设备发送所述网络性能分析信息,所述网络性能分析信息包括M个候选设备对应的网络性能分析信息,M为正整数;
    其中,一个候选设备对应的网络性能分析信息包括以下至少一种信息:
    所述一个候选设备的无线接入制式信息;
    所述一个候选设备可参与联邦学习的时间信息;
    所述一个候选设备的所处位置信息;
    所述一个候选设备存在网络覆盖的时间段信息;
    在感兴趣时间内,所述一个候选设备存在网络覆盖的时间段占所述感兴趣时间的比例信息;
    所述一个候选设备的网络信号质量信息。
  36. 根据权利要求35所述的装置,其中,所述第一请求消息包括上报粒度指示信息,所述上报粒度指示信息用于指示以设备为粒度,上报候选设备对应的网络性能。
  37. 根据权利要求35所述的装置法,其中,所述第一请求消息包括过滤信息,所述过滤信息包括以下至少一项:
    感兴趣区域;
    无线接入制式限定信息;
    所述感兴趣时间。
  38. 根据权利要求35至37中任一项所述的装置,其中,所述设备确定装置还包括获取单元和分析单元;
    获取单元,用于从第四通信设备获取M个候选设备的对应的网络性能数据;
    分析单元,用于对所述M个候选设备对应的网络性能数据进行分析,得到所述M个候选设备对应的网络性能分析信息。
  39. 根据权利要求38所述的装置,其中,所述获取单元包括第一获取子单元和第二获取子单元;
    所述第一获取子单元,用于从会话管理功能网元SMF获取所述M个候选设备对应的:无线接入制式信息、网络覆盖时间信息、会话在网络中的时间信息中的至少一项;
    所述第二获取子单元,用于从网络管理设备获取所述M个候选设备对应的:网络标识信息、网络信号质量信息中的至少一项。
  40. 根据权利要求35至37中任一项所述的装置,其中,所述设备确定装置还包括确定单元;
    所述确定单元,用于根据所述第一请求消息包括的过滤信息,确定所述M个候选设备,其中,所述M个候选设备中的每个候选设备满足以下至少一项条件:
    位于所述感兴趣区域内;
    无线接入制式为所述无线接入制式限定信息指示的无线接入制式;
    在所述感兴趣时间内,存在网络覆盖。
  41. 根据权利要求35所述的装置,其中,所述设备确定装置还包括确定单元;
    所述确定单元,用于确定所述M个候选设备具备联邦学习意愿;和/或,
    所述确定单元,用于确定所述M个候选设备具备联邦学习能力。
  42. 根据权利要求41所述的装置,其中,所述确定单元包括获取子单元和确定子单元;
    所述获取子单元,用于从第三通信设备获取所述M个候选设备的联邦学习意愿信息;
    所述确定子单元,用于根据所述M个候选设备的联邦学习意愿信息,确定所述M个候选设备具备联邦学习意愿。
  43. 根据权利要求41所述的装置,其中,所述确定单元包括获取子单元和确定子单元;
    所述获取子单元,用于从第三通信设备获取所述M个候选设备的联邦学习能力信息;
    所述确定子单元,用于根据所述M个候选设备的联邦学习能力信息,确定所述M个候选设备具备联邦学习能力。
  44. 一种通信设备,包括处理器和存储器,所述存储器存储可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执行时实现如权利要求1至24中任一项所述的设备确定方法的步骤。
  45. 一种可读存储介质,所述可读存储介质上存储程序或指令,所述程序或指令被处理器执行时实现如权利要求1-24中任一项所述的设备确定方法的步骤。
  46. 一种芯片,所述芯片包括处理器和通信接口,所述通信接口和所述处理器耦合,所述处理器用于运行程序或指令,实现如权利要求1-24中任一项所述的设备确定方法的步骤。
  47. 一种计算机程序产品,所述计算机程序产品被存储在非易失的存储介质中,所述计 算机程序产品被至少一个处理器执行以实现如权利要求1-24中任一项所述的设备确定方法的步骤。
  48. 一种电子设备,包括所述电子设备被配置成用于执行如权利要求1-24中任一项所述的设备确定方法的步骤。
PCT/CN2023/084339 2022-03-28 2023-03-28 设备确定方法、装置及通信设备 WO2023185818A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210314847.1A CN116866941A (zh) 2022-03-28 2022-03-28 设备确定方法、装置及通信设备
CN202210314847.1 2022-03-28

Publications (1)

Publication Number Publication Date
WO2023185818A1 true WO2023185818A1 (zh) 2023-10-05

Family

ID=88199195

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/084339 WO2023185818A1 (zh) 2022-03-28 2023-03-28 设备确定方法、装置及通信设备

Country Status (2)

Country Link
CN (1) CN116866941A (zh)
WO (1) WO2023185818A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102021100911A1 (de) * 2020-01-21 2021-07-22 Intel Corporation VERFAHREN UND VORRICHTUNGEN ZUM AUFTEILEN VON KI/ML-OPERATIONEN FÜR DATENANALYSE ZWISCHEN EINER NF EINES 5G-NETZES UND EINER AF GEMÄß EINER KI/ML-OPERATIONSRICHTLINIE
CN114079902A (zh) * 2020-08-13 2022-02-22 Oppo广东移动通信有限公司 联邦学习的方法和装置
WO2022059987A1 (ko) * 2020-09-18 2022-03-24 엘지전자 주식회사 사용자 데이터 분석 정보 외부 제공에 대한 사용자 동의를 획득, 관리 및 검증하는 방법 및 장치
CN115550849A (zh) * 2022-10-08 2022-12-30 广州爱浦路网络技术有限公司 终端设备选择方法、装置、网络设备及存储介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102021100911A1 (de) * 2020-01-21 2021-07-22 Intel Corporation VERFAHREN UND VORRICHTUNGEN ZUM AUFTEILEN VON KI/ML-OPERATIONEN FÜR DATENANALYSE ZWISCHEN EINER NF EINES 5G-NETZES UND EINER AF GEMÄß EINER KI/ML-OPERATIONSRICHTLINIE
CN114079902A (zh) * 2020-08-13 2022-02-22 Oppo广东移动通信有限公司 联邦学习的方法和装置
WO2022059987A1 (ko) * 2020-09-18 2022-03-24 엘지전자 주식회사 사용자 데이터 분석 정보 외부 제공에 대한 사용자 동의를 획득, 관리 및 검증하는 방법 및 장치
CN115550849A (zh) * 2022-10-08 2022-12-30 广州爱浦路网络技术有限公司 终端设备选择方法、装置、网络设备及存储介质

Also Published As

Publication number Publication date
CN116866941A (zh) 2023-10-10

Similar Documents

Publication Publication Date Title
CN110235412B (zh) 通信网络中的自适应业务处理
CN102404858B (zh) 一种无线资源优化方法、装置及系统
JP2022523364A (ja) ユーザプレーン経路選択方法及び装置
CN109982293B (zh) 流量产品推送方法、系统、电子设备及存储介质
WO2023169523A1 (zh) 数据采集方法、装置、终端及网络侧设备
WO2023185818A1 (zh) 设备确定方法、装置及通信设备
WO2023093894A1 (zh) 感知业务实现方法、装置、网络侧设备及终端
WO2022160670A1 (zh) Wi-Fi网络的识别方法和Wi-Fi网络的识别装置
CN111294856B (zh) 一种共享流量终端识别方法、装置、设备及可读存储介质
WO2023185788A1 (zh) 候选成员的确定方法、装置及设备
WO2023169425A1 (zh) 通信网络中的数据处理方法及网络侧设备
WO2023213288A1 (zh) 模型获取方法及通信设备
WO2023207980A1 (zh) 模型信息获取方法、发送方法、装置、节点和储存介质
WO2023185725A1 (zh) 数据获取方法、装置及网络侧设备
WO2023213246A1 (zh) 模型选择方法、装置及网络侧设备
WO2023179709A1 (zh) 信息处理方法、装置、通信设备及可读存储介质
WO2023179558A1 (zh) 数据采集方法及通信设备
WO2023185810A1 (zh) 终端路由选择策略ursp确定方法、终端及网络侧设备
TWI487414B (zh) Mobile network dynamic selection paging method
WO2023185826A1 (zh) 网元注册方法、模型请求方法、装置、网元、通信系统及存储介质
WO2024022398A1 (zh) 托管网络的选网信息的获取方法、终端及网络侧设备
WO2024061252A1 (zh) 信息获取方法、装置、网络侧设备及存储介质
WO2024027577A1 (zh) 数据特征分析方法、装置及网络设备
WO2023207870A1 (zh) 数据处理方法、终端及网络侧设备
WO2023179672A1 (zh) 用户面功能网元确定方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23778183

Country of ref document: EP

Kind code of ref document: A1