CN116567608A

CN116567608A - Communication method and device

Info

Publication number: CN116567608A
Application number: CN202210326157.8A
Authority: CN
Inventors: 封召; 辛阳; 王远
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2022-01-28
Filing date: 2022-03-29
Publication date: 2023-08-08

Abstract

A method and apparatus for communication, the method comprising: the first network element sends a first request message to the second network element, wherein the first request message is used for requesting data of a terminal equipment group, and terminal equipment in the terminal equipment group is terminal equipment participating in transverse federal learning. The first network element receives data of the terminal equipment group from the second network element, the data of the terminal equipment group comprises aggregation information of measurement results of QoS parameters, the first network element adjusts the QoS parameters of the first terminal equipment in the terminal equipment group according to the data of the terminal equipment group, and the first network element sends the adjusted QoS parameters of the first terminal equipment to the strategy control network element. By adopting the method, the efficiency of model training of federal learning can be improved.

Description

Communication method and device

The present application claims priority from the chinese patent office, application number 202210108437.1, application name "a communication method and apparatus" filed on 28, 2022, 01, the entire contents of which are incorporated herein by reference.

Technical Field

The embodiment of the application relates to the field of wireless communication, in particular to a communication method and device.

Background

Federal learning (federated learning, FL) is a machine learning framework that can effectively assist multiple users in data usage and machine learning modeling while meeting user privacy protection, data security, and government regulations. The federal learning is used as a distributed machine learning paradigm, so that the problem of data island can be effectively solved, joint modeling is carried out on the basis of not sharing user data, and further the data island is broken technically, and artificial intelligence (artificial intelligence, AI) cooperation is realized.

During model training for federal learning, existing quality of service (quality of service, qoS) parameter adjustment methods may affect the efficiency of model training for federal learning.

Disclosure of Invention

The application provides a communication method and device for improving efficiency of model training of federal learning.

In a first aspect, the present application provides a communication method, the method comprising: the method comprises the steps that a first network element sends a first request message to a second network element, wherein the first request message is used for requesting data of a terminal equipment group, and terminal equipment in the terminal equipment group is terminal equipment participating in transverse federal learning; the first network element receives data of the terminal equipment group from the second network element, wherein the data of the terminal equipment group comprises aggregation information of measurement results of QoS parameters; the first network element adjusts QoS parameters of first terminal equipment in the terminal equipment group according to the data of the terminal equipment group; and the first network element sends the adjusted QoS parameters of the first terminal equipment to a strategy control network element.

By adopting the method, the first network element subscribes the data of the terminal equipment group to the second network element, the second network element sends the data of the terminal equipment group to the first network element, and the first network element adjusts the QoS parameter of at least one terminal equipment in the terminal equipment group according to the data of the terminal equipment group, so that the efficiency of model training of federal learning can be improved.

In one possible design, the first request message includes indication information, where the indication information is used to indicate a measurement result of the QoS parameter of the feedback terminal device; the data of the terminal equipment group further comprises a measurement result of QoS parameters of a second terminal equipment in the terminal equipment group, wherein the second terminal equipment comprises the first terminal equipment.

With the above design, the second network element may also send the measurement result of the QoS parameter of the terminal device in the terminal device group to the first network element.

In one possible design, the first request message further includes a feedback condition for indicating a condition to be satisfied for feeding back a measurement result of the QoS parameter of the terminal device; and the measurement result of the QoS parameter of the second terminal equipment meets the feedback condition.

By adopting the design, the second network element can feed back the measurement result of the QoS parameters of the terminal equipment meeting the feedback condition.

In one possible design, the aggregation information includes an aggregate bit rate that characterizes a sum of bit rates of QoS flows of terminal devices in the group of terminal devices; when the first network element adjusts the QoS parameters of the first terminal equipment in the terminal equipment group according to the data of the terminal equipment group, if the aggregate bit rate is greater than the subscription maximum bit rate of the terminal equipment group, the first network element adjusts the bit rate of the QoS flow of the first terminal equipment according to the data of the terminal equipment group.

Illustratively, the first network element may adjust the bit rate of the QoS flow of at least one terminal device according to the data of the terminal device group, where the at least one terminal device includes the first terminal device, and after adjusting the bit rate of the QoS flow of the at least one terminal device, the sum of the bit rates of the QoS flows of the respective terminal devices in the terminal device group is less than or equal to the subscribed maximum bit rate.

By adopting the design, the QoS parameters of the terminal equipment can be adjusted, so that the sum of the bit rates of QoS flows of all the terminal equipment in the terminal equipment group is smaller than or equal to the subscription maximum bit rate.

In one possible design, the aggregation information includes statistics of transmission delays of terminal devices in the group of terminal devices; when the first network element adjusts the QoS parameters of the first terminal equipment in the terminal equipment group according to the data of the terminal equipment group, if the statistical value of the transmission time delay is larger than a first preset threshold value, the first network element adjusts the bit rate of the QoS flow of the first terminal equipment according to the data of the terminal equipment group.

The statistical value of the transmission delay of the terminal equipment in the terminal equipment group can be a variance determined according to the transmission delay of the terminal equipment in the terminal equipment group. The statistics of the transmission delays of the terminal devices in the group of terminal devices are illustratively the variances determined by the weighted transmission delays or the differential transmission delays of the terminal devices in the group of terminal devices.

By adopting the design, the QoS parameters of the terminal equipment can be adjusted, so that the statistical value of the transmission delay is smaller than or equal to a first preset threshold value.

In one possible design, the first terminal device is a terminal device whose transmission delay is greater than a second preset threshold or less than a third preset threshold, wherein the second preset threshold is greater than the third preset threshold.

By adopting the design, the transmission delay of the terminal equipment with longer transmission delay can be reduced, the sum of the bit rates of QoS flows of the terminal equipment in the terminal equipment group is smaller than or equal to the contracted maximum bit rate, the transmission delay of the terminal equipment with shorter transmission delay can be increased, and the data sent to the server by the terminal equipment in the terminal equipment group almost arrives at the server at the same time, so that the efficiency of model training of federal learning is improved.

In one possible design, the first request message further includes the first preset threshold and/or the second preset threshold.

In one possible design, the first request message includes at least one of an identification of a terminal device included in the terminal device group, an identification of the terminal device group, identification information of an analysis type, and a type of the aggregation information.

In one possible design, the first request message further includes at least one of: sending the triggering condition of the aggregation information; and the application identifier is used for indicating the application corresponding to the measurement result of the QoS parameter of the terminal equipment.

The triggering condition for sending the aggregation information may include periodically feeding back the aggregation information, or feeding back the aggregation information while satisfying a preset condition. For example, the preset conditions herein may include that the aggregate bit rate is greater than the subscribed maximum bit rate of the group of terminal devices, and/or that the statistical value of the transmission delays of the terminal devices in the group of terminal devices is greater than the first preset threshold, etc.

In one possible design, the first network element is an application function network element, and the second network element is a data analysis function network element or a policy control network element.

In a second aspect, the present application provides a communication method, the method comprising: the second network element receives a first request message from the first network element, wherein the first request message is used for requesting data of a terminal equipment group, and terminal equipment in the terminal equipment group is terminal equipment participating in transverse federal learning; and the second network element sends the data of the terminal equipment group, wherein the data of the terminal equipment group comprises aggregation information of the measurement result of the QoS parameters.

By adopting the method, the first network element subscribes the data of the terminal equipment group to the second network element, and the second network element sends the data of the terminal equipment group to the first network element, so that the first network element adjusts the QoS parameter of at least one terminal equipment in the terminal equipment group according to the data of the terminal equipment group, and further the efficiency of model training of federal learning can be improved.

In one possible design, the aggregation information includes an aggregate bit rate that characterizes a sum of bit rates of QoS flows of the terminal devices in the group of terminal devices.

In one possible design, the aggregation information includes statistics of transmission delays of the terminal devices in the group of terminal devices.

In one possible design, the first request message includes at least one of an identification of a terminal device in the terminal device group, an identification of the terminal device group, identification information of an analysis type, and a type of the aggregation information.

In one possible design, the method further comprises: the second network element sends a second request message to the user plane network element, wherein the second request message is used for requesting the data of the terminal equipment group; the second network element receives the data of the terminal equipment group from the user plane network element.

By adopting the design, the second network element can directly acquire the data of the terminal equipment group from the user plane network element.

In one possible design, the method further comprises: the second network element sends a third request message to the user plane network element, wherein the third request message is used for requesting the measurement result of the QoS parameters of the terminal equipment in the terminal equipment group; the second network element receives a measurement result of the QoS parameters of the terminal equipment in the terminal equipment group from the user plane network element; the second network element determines data of the terminal equipment group according to the measurement result of the QoS parameters of the terminal equipment in the terminal equipment group and the first request message.

By adopting the design, the second network element can aggregate the measurement results of the QoS parameters of the terminal equipment obtained from the user plane network element to obtain the data of the terminal equipment group.

In one possible design, the second network element is a policy control network element; the method further comprises the steps of: the second network element receives the bit rate of QoS flows respectively corresponding to each terminal device included in the terminal device group from the first network element; the second network element receives the subscription maximum bit rate of the terminal equipment group from a third network element, wherein the third network element is a unified data storage network element or a unified data management network element; the second network element determines that the sum of the bit rates of the QoS flows respectively corresponding to the terminal equipment included by the terminal equipment group is smaller than the subscription maximum bit rate of the terminal equipment group according to the subscription maximum bit rate of the terminal equipment group and the bit rates of the QoS flows respectively corresponding to the terminal equipment included by the terminal equipment group; the second network element generates PCC rules respectively corresponding to each terminal device included in the terminal device group; and the second network element sends the PCC rule to a session management network element.

In one possible design, the second network element is a policy control network element; the method further comprises the steps of: the second network element receives the bit rate reference range of QoS flows respectively corresponding to each terminal device included in the terminal device group from the first network element; the second network element receives the subscription maximum bit rate of the terminal equipment group from a third network element, wherein the third network element is a unified data storage network element or a unified data management network element; the second network element determines that the sum of the lower bounds of the bit rate reference ranges of the QoS flows respectively corresponding to the terminal equipment included by the terminal equipment group is smaller than the subscription maximum bit rate of the terminal equipment group according to the subscription maximum bit rate of the terminal equipment group and the bit rate reference ranges of the QoS flows respectively corresponding to the terminal equipment included by the terminal equipment group; the second network element generates PCC rules respectively corresponding to each terminal device included in the terminal device group; and the second network element sends the PCC rule to a session management network element.

By adopting the design, the policy control network element can determine whether the subscription maximum bit rate of the terminal equipment group is met according to the bit rate value of the QoS stream respectively corresponding to each terminal equipment included in the terminal equipment group or the bit rate value range of the QoS stream respectively corresponding to each terminal equipment included in the terminal equipment group.

In one possible design, the method further comprises: and the second network element sends second information to the first network element, wherein the second information indicates that corresponding PCC rules are respectively generated for each terminal device included by the terminal device group.

In a third aspect, an embodiment of the present application provides a communication device, where the device is a first network element, or a device for implementing a function of the first network element, where the device includes a processing module and a transceiver module; the receiving and transmitting module is configured to send a first request message to a second network element, where the first request message is used to request data of a terminal device group, where terminal devices in the terminal device group are terminal devices participating in horizontal federal learning; receiving data of the terminal equipment group from the second network element, wherein the data of the terminal equipment group comprises aggregation information of measurement results of QoS parameters; the processing module is used for adjusting the QoS parameters of the first terminal equipment in the terminal equipment group according to the data of the terminal equipment group; and the receiving and transmitting module is used for transmitting the adjusted QoS parameters of the first terminal equipment to the strategy control network element.

In one possible design, the first request message includes indication information indicating a measurement result of the QoS parameter of the feedback terminal device;

the data of the terminal equipment group further comprises a measurement result of QoS parameters of a second terminal equipment in the terminal equipment group, wherein the second terminal equipment comprises the first terminal equipment.

In one possible design, the first request message further includes a feedback condition indicating a condition that needs to be met for feeding back a measurement result of the QoS parameter of the terminal device; and the measurement result of the QoS parameter of the second terminal equipment meets the feedback condition.

In one possible design, the aggregation information includes an aggregate bit rate that characterizes a sum of bit rates of QoS flows of terminal devices in the group of terminal devices; the processing module is configured to adjust, when the QoS parameter of a first terminal device in the terminal device group is adjusted according to the data of the terminal device group, if the aggregate bit rate is greater than the subscription maximum bit rate of the terminal device group, the bit rate of the QoS flow of the first terminal device according to the data of the terminal device group.

In one possible design, the aggregation information includes statistics of transmission delays of terminal devices in the group of terminal devices; the processing module is configured to adjust, when the QoS parameter of a first terminal device in the terminal device group is adjusted according to the data of the terminal device group, if the statistical value of the transmission delay is greater than a first preset threshold, the bit rate of the QoS flow of the first terminal device according to the data of the terminal device group.

In one possible design, the first terminal device is a terminal device whose transmission delay is greater than a second predetermined threshold.

In a fourth aspect, the present application provides a communication device, where the device is a second network element, or a device for implementing a function of the second network element, and the device includes a processing module and a transceiver module; the processing module calls the transceiver module to execute: receiving a first request message from a first network element, wherein the first request message is used for requesting data of a terminal equipment group, and the terminal equipment in the terminal equipment group is terminal equipment participating in horizontal federal learning; and sending the data of the terminal equipment group, wherein the data of the terminal equipment group comprises aggregation information of the measurement result of the QoS parameters.

In one possible design, the first request message includes indication information indicating a measurement result of the QoS parameter of the feedback terminal device; the data of the terminal equipment group further comprises a measurement result of QoS parameters of a second terminal equipment in the terminal equipment group, wherein the second terminal equipment comprises the first terminal equipment.

In one possible design, the transceiver module is further configured to send a second request message to a user plane network element, where the second request message is used to request data of the terminal device group; and receiving the data of the terminal equipment group from the user plane network element.

In one possible design, the transceiver module is further configured to send a third request message to a user plane network element, where the third request message is used to request a measurement result of a QoS parameter of a terminal device in the terminal device group; receiving a measurement result of QoS parameters of terminal devices in the terminal device group from the user plane network element; the processing module is further configured to determine data of the terminal equipment group according to a measurement result of QoS parameters of terminal equipment in the terminal equipment group and the first request message.

In a fifth aspect, the present application provides a communication method, the method comprising: the method comprises the steps that an application function network element obtains transmission delay and local calculation delay of each terminal device in a terminal device group, wherein the terminal devices in the terminal device group are terminal devices participating in transverse federal learning, and the application function network element adjusts QoS parameters of a first terminal device in the terminal device group according to the transmission delay and the local calculation delay of each terminal device; and the application function network element sends the adjusted QoS parameters of the first terminal equipment to a strategy control network element.

By adopting the method, the application function network element can collect data without NWDAF or PCF, and count or acquire the transmission delay and the local calculation delay of each terminal device in the terminal device group, so as to further determine the adjustment strategy of QoS parameters of the terminal devices in the terminal device group, reduce the number of messages interacted between network elements, lighten the load of the network elements, and improve the QoS parameter adjustment efficiency of the terminal devices, so that the sum of the local calculation delay and the transmission delay of different terminal devices is approximately the same, and the model training efficiency of transverse federal learning is improved.

In one possible design, when the application function network element adjusts QoS parameters of a first terminal device in the terminal device group according to the transmission delay and the local computation delay of each terminal device, the application function network element determines a statistic value of total delay of each terminal device according to the transmission delay and the local computation delay of each terminal device, where the total delay of each terminal device is a sum of the transmission delay and the local computation delay of the terminal device; and when the total time delay of the first terminal equipment is larger than a first preset threshold or smaller than a second preset threshold, the application function network element adjusts the QoS parameters of the first terminal equipment, wherein the first preset threshold and the second preset threshold are determined according to the statistic value.

In one possible design, the adjusted QoS parameter of the first terminal device includes at least one of a resource type, a priority, a packet delay budget, a guaranteed stream bit rate, a maximum stream bit rate, an allocation and a preemption priority.

In one possible design, the local computation time delay is a length of time required to determine update parameters of the model of the lateral federal learning; the transmission delay is a time period required for transmitting the update parameter to the application function network element.

In a sixth aspect, the present application provides a communications device, where the device is an application function network element, or a device for implementing a function of the application function network element, the device includes a processing module and a transceiver module; the processing module is used for acquiring the transmission delay and the local computation delay of each terminal device in the terminal device group, wherein the terminal devices in the terminal device group are terminal devices participating in transverse federal learning, and the QoS parameters of the first terminal devices in the terminal device group are adjusted according to the transmission delay and the local computation delay of each terminal device; and the receiving and transmitting module is used for transmitting the adjusted QoS parameters of the first terminal equipment to the strategy control network element.

In one possible design, when adjusting QoS parameters of a first terminal device in the terminal device group according to the transmission delay and the local computation delay of each terminal device, the processing module is configured to determine a statistic value of total delay of each terminal device according to the transmission delay and the local computation delay of each terminal device, where the total delay of each terminal device is a sum of the transmission delay and the local computation delay of the terminal device; and under the condition that the total time delay of the first terminal equipment is larger than a first preset threshold value or smaller than a second preset threshold value, adjusting the QoS parameters of the first terminal equipment, wherein the first preset threshold value and the second preset threshold value are determined according to the statistic value.

In a seventh aspect, the present application also provides an apparatus. The apparatus may perform the above method design. The apparatus may be a chip or a circuit capable of performing the functions corresponding to the above-described methods, or a device including the chip or the circuit.

In one possible implementation, the apparatus includes: a memory for storing computer executable program code; and a processor coupled to the memory. Wherein the program code stored in the memory comprises instructions which, when executed by the processor, cause the apparatus or device in which the apparatus is installed to carry out the method of any one of the possible designs described above.

In one possible implementation, the apparatus may further comprise a communication interface, which may be a transceiver, or if the apparatus is a chip or a circuit, the communication interface may be an input/output interface of the chip, such as an input/output pin or the like.

In one possible design, the device comprises corresponding functional units for implementing the steps in the above method, respectively. The functions may be realized by hardware, or may be realized by hardware executing corresponding software. The hardware or software includes one or more units corresponding to the above functions.

In an eighth aspect, the present application provides a computer readable storage medium storing a computer program which, when run on a device, performs the method of any one of the possible designs described above.

In a ninth aspect, the present application provides a computer program product comprising a computer program for performing the method of any one of the above possible designs when the computer program is run on a device.

In a tenth aspect, the present application provides a communication system comprising a first network element for performing the method in any one of the possible designs of the first aspect and a second network element for performing the method in any one of the possible designs of the second aspect.

Drawings

Fig. 1 is a schematic architecture diagram of a mobile communication system applied in the present application;

FIG. 2 is a schematic diagram of a dataset participating in lateral federal learning in an embodiment of the present application;

FIG. 3 is a schematic diagram of a model training process for lateral federal learning in an embodiment of the present application;

FIG. 4 is an overview flowchart of a communication method in an embodiment of the present application;

fig. 5A is a schematic diagram of a transmission delay of a terminal device in a terminal device group before adjustment in an embodiment of the present application;

fig. 5B is a schematic diagram of a transmission delay of a terminal device in the adjusted terminal device group according to an embodiment of the present application;

fig. 6 is a flowchart of interaction between a first network element and other network elements before the first network element sends a first request message to a second network element in an embodiment of the present application;

FIG. 7 is an overview flowchart of another communication method in an embodiment of the present application;

FIG. 8 is an overview flow chart of another communication method in an embodiment of the present application;

FIG. 9 is an overview flowchart of another communication method in an embodiment of the present application;

FIG. 10 is a flow chart illustrating interaction between AF and PCF in an embodiment of the present application;

fig. 11 is a schematic structural diagram of a communication device according to an embodiment of the present application;

fig. 12 is a second schematic structural diagram of a communication device according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. The terms first, second and the like in the description and claims of the present application and in the above-described figures, and the like, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the terms so used are interchangeable under appropriate circumstances and are merely illustrative of the manner in which the embodiments of the application described herein have been described for objects of the same nature. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of elements is not necessarily limited to those elements, but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.

In the description of the present application, "/" means or, unless otherwise indicated, for example, a/B may represent a or B; the term "and/or" in this application is merely an association relation describing an association object, and means that three kinds of relations may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. In addition, in the description of the present application, "at least one" means one or more items, and "multiple" means two or more items. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b, or c may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or plural.

The technical scheme provided by the embodiment of the application can be applied to various communication systems. For example: the method can be applied to an LTE system or a 5G system, can also be applied to other new systems facing the future, and the like. The embodiment of the present application is not particularly limited thereto. Furthermore, the term "system" may be interchangeable with "network". The following description will be given by taking a 5G communication system architecture as an example.

As shown in fig. 1, a 5G communication system is defined by the third generation partnership project (3rd generation partnership project,3GPP) standard. The communication system comprises a terminal device (e.g. User Equipment (UE)), a radio access network (radio access network, RAN), a Core Network (CN). In logic, network elements of a core network can be divided into a user plane and a control plane, the control plane is responsible for management of a mobile network, and the user plane is responsible for transmission of service data.

The terminal equipment is an entrance for interaction between the mobile user and the network, can provide basic computing capacity and storage capacity, displays a service window for the user, and receives user operation input. The next generation of terminal devices (NextGen UEs) can use the new air interface technology to establish signal connections, data connections, and thus transmit control signals and traffic data to the mobile network. The terminal device may include various handheld devices, vehicle mount devices, wearable devices, computing devices, or other processing devices connected to a wireless modem, as well as various forms of terminals, mobile Stations (MSs), terminals, soft terminals, etc., such as water meters, electricity meters, sensors, etc.

RAN: the network access function is provided for authorized users in a specific area, and transmission tunnels with different qualities can be determined according to the level of the users, the service requirements and the like to transmit user data. The RAN can manage its own resources, make reasonable use of, provide access services for the terminal devices as needed, and is responsible for forwarding control signals and user data between the terminal devices and the core network.

Core network: and the system is responsible for maintaining subscription data of the mobile network, managing network elements of the mobile network, and providing session management, mobility management, policy management, security authentication and other functions for the terminal equipment. Providing network access authentication for the terminal equipment when the terminal equipment is attached; when the terminal equipment has a service request, network resources are allocated to the terminal equipment; updating network resources for the terminal equipment when the terminal equipment moves; providing a quick recovery mechanism for the terminal equipment when the terminal equipment is idle; releasing network resources for the terminal equipment when the terminal equipment is detached; providing a data routing function for the terminal device, such as forwarding uplink data to the data network, when the terminal device has service data; or receiving the downlink data of the terminal equipment from the data network, and forwarding the downlink data to the RAN so as to be sent to the terminal equipment by the RAN.

Data Network (DN): the data network for providing business services for users, in general, the client is located in the terminal device, and the server is located in the data network. The data network may be a private network, such as a local area network, or an external network not under the control of the operator, such as the Internet (Internet), or a proprietary network co-deployed by the operator, such as a network providing IP multimedia network subsystem (IP multimedia core network subsystem, IMS) services.

Wherein the core network user plane comprises a user plane function (user plane function, UPF); the core network control plane includes access and mobility management functions (access and mobility management function, AMF), session management functions (session management function, SMF), network opening functions (network exposure function, NEF), network function warehousing functions (NF repository function, NRF), unified data management (unified data management, UDM), unified data storage (unified data repository, UDR), policy control functions (policy control function, PCF), application functions (application function, AF).

The control plane of the core network adopts a service architecture, and the interaction between the network elements of the control plane adopts a service calling mode to replace a point-to-point communication mode in the traditional architecture. In the service architecture, the control plane network element can open services to other control plane network elements for calling by the other control plane network elements; in point-to-point communication, a communication interface between control plane network elements stores a set of specific messages, which can only be used by the control plane network elements at both ends of the interface during communication.

The following briefly describes the functions of the functional entities in the core network:

1. session management network element: the method is mainly used for session management, IP address allocation and management of terminal equipment, terminal node of selecting manageable user equipment plane function, strategy control or charging function interface, downlink data notification and the like. In 5G communications, the session management network element may be an SMF network element, and in future communications, such as 6G communications, the session management function network element may still be an SMF network element, or have other names, which are not limited in this application. Nsmf is a service-based interface provided by the SMF, which may communicate with other network functions through Nsmf.

2. Access management network element: the method is mainly used for mobility management, access management and the like, and can be a mobility management entity (mobility management entity, MME) function in a 4G communication network or an AMF network element in a 5G network. In future communications, such as 6G communications, the access management network element may still be an AMF network element, or have other names, which are not limited in this application. Namf is a service-based interface provided by AMFs, which may communicate with other network functions through the Namf.

3. Network opening network element: for securely opening services and capabilities provided by 3GPP network functions, etc., to the outside. In 5G communications, the network open network element may be a NEF network element, and in future communications, such as 6G communications, the network open function network element may still be a NEF network element, or have other names, which is not limited in this application. Where Nnef is a service-based interface provided by the NEF, which may communicate with other network functions through the Nnef.

4. Network storage network element: for providing service registration, discovery and authorization, and maintaining available Network Function (NF) instance information, on-demand configuration of network functions and services and interconnection between NFs may be implemented. In 5G communications, the network storage element may be an NRF element, and in future communications, such as 6G communications, the network storage function element may still be an NRF element, or have other names, which are not limited in this application. The nrrf is a service-based interface provided by the NRF, which can communicate with other network functions through the nrrf.

5. Policy control network element: a unified policy framework for guiding network behavior, providing policy rule information for control plane function network elements (e.g., AMFs, SMFs, etc.), and the like. In 5G communications, the policy control network element may be a PCF network element, and in future communications, such as 6G communications, the policy control network element may still be a PCF network element, or have other names, which is not limited in this application. Where Npcf is a service-based interface provided by the PCF, the PCF may communicate with other network functions through the Npcf.

6. Data management network element: for handling subscriber identities, subscriptions, access authentication, registration, or mobility management, etc. In 5G communications, the data management network element may be a UDM network element, and in future communications, such as 6G communications, the data management network element may still be a UDM network element, or have other names, which is not limited in this application. Where Nudm is a service-based interface provided by the UDM, which may communicate with other network functions through Nudm.

7. A data storage network element: the access function is used for executing the subscription data, the strategy data, the application data and other types of data. In 5G communications, the data storage network element may be a UDR network element, and in future communications, such as 6G communications, the data storage network element may still be a UDR network element, or have other names, which is not limited in this application. Where Nudr is a service-based interface provided by the UDR, which may communicate with other network functions through Nudr.

8. Application network element: for performing application-influenced data routing, accessing network open functions, or interacting with policy frameworks for policy control, etc. In 5G communication, the application network element may be an AF network element, and in future communication, such as 6G communication, the application network element may still be an AF network element, or have other names, which is not limited in this application. Naf is a service-based interface provided by the AF, which may communicate with other network functions through Naf.

9. User plane network element: quality of service (quality of service, qoS) handling for packet routing and forwarding, or user plane data, etc. In 5G communications, the user plane element may be a user plane function (user plane function, UPF) element, and in future communications, such as 6G communications, the user plane element may still be a UPF element, or have other names, which are not limited in this application.

It will be appreciated that the core network may also include other network elements, which are not limited in this application.

To facilitate an understanding of the embodiments of the present application, several basic concepts involved in the embodiments of the present application are briefly described.

1. Lateral federal learning

Federal learning can be divided into three categories depending on the nature of the data sources of the parties involved in federal learning: horizontal federal learning, vertical federal learning, and federal migration learning. The following mainly describes the principles of lateral federal learning.

The data set comprises a plurality of groups of data, each group of data corresponds to one user, and each group of data records at least one user characteristic of the user corresponding to the group of data.

Wherein, between the data sets of the lateral federal learning, the user characteristics (X1, X2, X3 … …) overlap ratio is high, the user (U1, U2, U3 … …) overlap ratio is low, for example, the data set a includes data of UE1 and data of UE2, the data of UE1 includes user characteristics of X1, X2 and X3, the data of UE2 includes user characteristics of X1, X2 and X3, the data set B includes data of UE4 and data of UE5, the data of UE4 includes user characteristics of X1, X2 and X3, and the data of UE5 includes user characteristics of X1, X2 and X3. As shown in fig. 2, for data set a and data set B, the user's intersection is smaller and the user's intersection of features is larger. Thus, data set A and data set B may pick the same user features from their respective data sets for model training for lateral federal learning. It should be noted that the participants of the lateral federal learning are not limited to two parties, such as in an internet of things (internet of things, ioT) scenario, which may be very bulky.

Fig. 3 shows the training process of the transverse federal learning model by means of the 5G system (5G system,5 gs) for intermediate result transmission. In the model training process of the horizontal federal learning, first, each participant (user (Client) 1, client2 … … Client k as shown in fig. 3) needs to download the latest model from the Server (Server) through 5GS to iterate the model training process, and the specific iteration process generally includes the following steps:

(1) each participant calculates the gradient of the model using the local dataset and then uploads the gradient encryption to the Server. The gradient here includes the direction and magnitude of the change in parameters of the model.

(2) And the Server performs gradient aggregation according to the gradients uploaded by each participant and updates the parameters of the model. Gradient aggregation here generally refers to averaging the collected gradients.

(3) The Server distributes the parameters of the updated model to each participant.

(4) Each participant updates the local model according to the updated parameters of the model.

2. Quality of service (quality of service, qoS)

QoS describes a set of service requirements that a network must meet to ensure the proper service level for data transmission.

The 5G network needs to support various traffic transmissions such as video, mobile payment, web browsing, factory automation control, etc. QoS required for different services is different. For example, video services require greater bandwidth, while automated control services generally require lower latency and higher reliability. Based on the QoS framework of the 5G network, operators can provide different QoS guarantees for different services.

In 5G networks, quality of service Flow (QoS Flow) is the finest granularity of end-to-end QoS control in a protocol data unit (protocol data unit, PDU) session. QoS control of QoS Flow is primarily determined by the QoS parameters associated therewith. The 5G network-based QoS framework supports guaranteed bandwidth QoS Flow (QoS Flows that require guaranteed Flow bit rate, GBR QoS Flow) and Non-guaranteed bandwidth QoS Flow (QoS Flows that do not require guaranteed Flow bit rate, non-GBR QoS Flow). For GBR QoS Flow, the network needs to reserve resources to guarantee its bandwidth. No resources need to be reserved for Non-GBR QoS flows. The corresponding QoS parameters for GBR and non-GBR QoS flows are shown in Table 1.

Table 1: qoS parameters for different types of QoS flows

Wherein 5QI is used to identify a set of 5G QoS features. The 5G QoS feature is used to describe the case of end-to-end packet forwarding processing of QoS flows between UE and UPF, including resource types (such as Non-GBR and GBR), priority, packet delay budget (packet delay budget, PDB), and packet error rate, etc.

It should be noted that, the QoS parameters are all for a single QoS Flow. In addition to this, some aggregated QoS parameters are defined in 5G networks. The aggregate QoS parameters are used to characterize statistical properties of QoS parameters of multiple QoS flows, e.g., aggregate maximum bit rate (aggregate maximum bit rate, AMBR) that is used to limit the maximum of a set of QoS Flow total bit rates.

According to the granularity of data, some different levels of AMBR parameters are defined in the existing 5G standard:

aggregate maximum bit rate at PDU Session level (Session-AMBR): the aggregate bit rate expected to be provided in all Non-GBR QoS flows for a particular PDU session is limited.

UE-level aggregate maximum bit rate (UE-AMBR): the method is suitable for Non-GBR QoS Flow.

Maximum bit rate per Slice level for each UE (UE-Slice-MBR): the aggregate bit rate expected to be provided in all GBR QoS flows and Non-GBR QoS flows for PDU sessions for a particular slice-specific UE is limited.

Maximum bit rate at Slice level (Slice-mbrper S-NSSAI): the method is suitable for GBRQoS Flow and Non-GBR QoS Flow.

It can be understood that the method provided by the application can be applied to a scenario of horizontal federal learning, and can also be applied to other model training processes or business processes requiring interaction between a server and terminal devices in a terminal device group, and the scenario of horizontal federal learning is described below as an example.

In the model training process of federal learning, in order to realize adjustment of QoS parameters of different participants, the model training efficiency is improved. The present application provides a communication method, as shown in fig. 4, where the following first network element may be an application function network element, and the second network element may be a data analysis function network element or a policy control network element. Illustratively, the data analysis function network element may refer to a network data analysis function (network data analytics Function, NWDAF) network element, and the policy control network element may refer to a PCF network element.

The method comprises the following steps:

step 400: the first network element sends a first request message to the second network element, wherein the first request message is used for requesting data of a terminal equipment group, and the data of the terminal equipment group comprises aggregation information of measurement results of QoS parameters.

The first request message may also be referred to as a first subscription message, and the name of the first request message is not limited in this application. For example, when the second network element is an NWDAF network element, the first request message may be an analysis subscription message (nnwdaf_analysis subscription_subscription). When the second network element is a PCF network element, the first request message may be an event open subscription message (nnwdaf_ EventExposure Subscribe).

The terminal equipment group comprises at least two terminal equipment. The terminal devices in the terminal device group may be terminal devices participating in lateral federal learning. The terminal devices in the terminal device group illustratively participate in the model training process of the same lateral federal learning.

Furthermore, it should be noted that, before the first network element sends the first request message to the second network element, the terminal devices in the terminal device group have established a session of the service associated with the lateral federal learning. For example, the first service is a model training service of some kind of lateral federal learning, the group of terminal devices comprises 3 terminal devices, which 3 terminal devices are participants of the first service, which 3 terminal devices have established a session with respect to the first service.

Wherein the aggregation information may also be referred to as aggregated QoS information, which is determined by aggregation according to measurement results of QoS parameters of respective terminal devices in the terminal device group. The aggregation information is used for representing statistical characteristics of measurement results of QoS parameters of each terminal device included in the terminal device group. The QoS parameters of the terminal device herein may refer to the relevant description above regarding QoS parameters.

Illustratively, the first request message may include, but is not limited to, the following:

1. and the analysis type identification information is used for indicating that the aggregation information is the aggregation information of the terminal equipment group, namely the aggregation information of the terminal equipment group level.

Illustratively, the identification information may be represented by an analysis identification (analysis ID), for example, analysis id= Aggregated QoS for FL group, representing aggregated information of the request FL group (group).

2. The type of the aggregation information is used for indicating parameters included in the aggregation information. The type of aggregation information may be represented by an aggregate QoS parameter (Aggregated QoS parameters to be measured) that needs to be measured, for example.

The type of the aggregation information may specifically include an aggregation bit rate, a statistic value of a transmission delay of the terminal devices in the terminal device group, and the like. It will be appreciated that the parameter information may also include other parameters according to the model training business requirements of the lateral federal learning, and is not limited herein.

Wherein the aggregate bit rate is used to characterize the sum of the bit rates of the QoS flows of the terminal devices in the group of terminal devices. In addition, according to the conversion relation between the bit rate and the bandwidth, the aggregate bit rate can be converted into an aggregate bandwidth, and the aggregate bandwidth is used for representing the sum of bandwidths corresponding to the terminal devices in the terminal device group.

It is to be understood that, here, the QoS flows are QoS flows corresponding to the lateral federal learning service, and, unless otherwise stated, the QoS flows referred to hereinafter refer to QoS flows corresponding to the lateral federal learning service. The bit rate of the QoS flow here may be referred to as GFBR.

Illustratively, during model training of lateral federal learning, each participant needs to perform a local calculation and upload the calculation result to a server, and therefore, a large amount of bandwidth resources will be consumed. To avoid affecting other terminal devices or other services, a maximum available bandwidth is typically set for the model training service of the lateral federal learning. In order to ensure that the sum of the bandwidths of the respective participants does not exceed the set maximum available bandwidth, the first network element may subscribe to an aggregate bandwidth with the second network element and adjust the bandwidth of at least one participant when the aggregate bandwidth is greater than the set maximum available bandwidth. For specific adjustments, reference may be made to the associated description in step 420 below.

The statistical value of the transmission delay of the terminal equipment in the terminal equipment group can be a variance determined according to the transmission delay of the terminal equipment in the terminal equipment group.

The statistics of the transmission delays of the terminal devices in the terminal device group are exemplified by variances determined by the weighted transmission delays of the terminal devices in the terminal device group (hereinafter referred to simply as variances of the weighted transmission delays) or by the differential transmission delays of the terminal devices in the terminal device group (hereinafter referred to simply as variances of the differential transmission delays). Taking any one of the terminal devices in the terminal device group (denoted as terminal device a) as an example, the weighted transmission delay of the terminal device a is a ratio of an actual transmission delay of the terminal device a to an expected transmission delay of the terminal device a, the differential transmission delay of the terminal device a is a difference between the actual transmission delay of the terminal device a and the expected transmission delay of the terminal device a, the actual transmission delay of the terminal device a is a time interval between a sending time of a QoS stream of the terminal device a and a time when the QoS stream of the terminal device a arrives at the server, and the expected transmission delay of the terminal device a is a time interval between a sending time of the QoS stream of the terminal device a and a preset time. The actual transmission delay of the terminal equipment a may be obtained by a measurement result of the QoS parameter of the terminal equipment a, and the expected transmission delay of the terminal equipment a may be sent from the first network element to the second network element in step 400, or may be configured to the second network element or the user plane network element in advance.

It will be appreciated that the server may be co-located with any network element or may be a separate server. The actual transmission delay of the first terminal device may be a PDB of the first terminal device.

As shown in fig. 5A, the terminal device group includes UE1, UE2, and UE3, each UE corresponds to a time axis, a time length from a start point of the time axis to a triangle mark corresponds to a local calculation completion time of the UE, a time length from the triangle mark to a circle mark corresponds to an actual transmission delay of the UE, and a time length from the triangle mark to an intersection point of a first dotted line and the time axis corresponds to an expected transmission delay of the UE. The first dashed line location may be understood as the time when the server receives the calculation result of the last UE (i.e. UE 2). The local calculation completion time of each UE may be different and difficult to change, i.e. the positions of the triangle marks in fig. 5A are different, and the transmission delay of each UE may also be different, i.e. the positions of the circle marks in fig. 5A are different, but the transmission delay of the UE may be achieved by adjusting the bandwidth of the UE.

Illustratively, the weighted transmission delay of UE1 = actual transmission delay of UE 1/expected transmission delay of UE1, the weighted transmission delay of UE2 = actual transmission delay of UE 2/expected transmission delay of UE2, the weighted transmission delay of UE3 = actual transmission delay of UE 3/expected transmission delay of UE 3; alternatively, the weighted transmission delay of UE 1=the expected transmission delay of UE 1/the actual transmission delay of UE1, the weighted transmission delay of UE 2=the expected transmission delay of UE 2/the actual transmission delay of UE2, and the weighted transmission delay of UE 3=the expected transmission delay of UE 3/the actual transmission delay of UE 3. The larger the variance determined by the weighted transmission delay of UE1, the weighted transmission delay of UE2 and the weighted transmission delay of UE3, the larger the time difference that the QoS flows respectively transmitted by the three reach the server, and the smaller the variance, the smaller the time difference that the QoS flows respectively transmitted by the three reach the server.

Illustratively, differential transmission delay of UE1 = actual transmission delay of UE 1-expected transmission delay of UE1, differential transmission delay of UE2 = actual transmission delay of UE 2-expected transmission delay of UE2, differential transmission delay of UE3 = actual transmission delay of UE 3-expected transmission delay of UE 3; alternatively, differential transmission delay of UE1 = expected transmission delay of UE 1-actual transmission delay of UE1, differential transmission delay of UE2 = expected transmission delay of UE 2-actual transmission delay of UE2, differential transmission delay of UE3 = expected transmission delay of UE 3-actual transmission delay of UE 3. The larger the variance determined by the differential transmission delay of UE1, the differential transmission delay of UE2 and the differential transmission delay of UE3, the larger the time difference that the QoS flows respectively transmitted by the three reach the server, and the smaller the variance, the smaller the time difference that the QoS flows respectively transmitted by the three reach the server.

Illustratively, according to the principles of lateral federal learning, the server needs to update the model after receiving the calculation results of the individual participants. When the time difference between the calculation results of each participant and the server is large, that is, the variance determined by the weighted transmission delay or the differential transmission delay of each participant is large, the overall training period is prolonged, and the model training efficiency is reduced. When the calculated results of all the participants are transmitted to the server in approximately the same time, that is, the variance determined by the weighted transmission delay or the differential transmission delay of all the participants is smaller, the waiting time of the server can be reduced, and the model training efficiency is further improved. Therefore, the first network element may subscribe to the variance with the second network element, and adjust the transmission delay of at least one participant when the variance is greater than the set variance threshold, and the specific adjustment may be described in the following step 420.

Illustratively, according to the principles of lateral federal learning, the server needs to update the model after receiving the calculation results of the individual participants. When the time difference between the calculation results of each participant and the server is larger, that is, the variance determined by the weighted transmission delay of each participant is larger, the overall training period is prolonged, and the model training efficiency is reduced. When the calculated results of all the participants are transmitted to the server in approximately the same time, that is, the variance determined by the weighted transmission delay of all the participants is smaller, the waiting time of the server can be reduced, and the model training efficiency is further improved. Therefore, the first network element may subscribe to the variance with the second network element, and adjust the transmission delay of at least one participant when the variance is greater than the set variance threshold, and the specific adjustment may be described in the following step 420.

3. Information indicating the group of terminal devices. The information for indicating the terminal device group may include, for example, an identification of each terminal device in the terminal device group, or a terminal device list corresponding to the terminal device group, or an identification of the terminal device group, or the like. For example, the information indicating the group of terminal devices may be identified by the target (Target of analytics reporting) of the analysis report.

For example, the terminal equipment group includes UE1, UE2, and UE3, and the information for indicating the terminal equipment group includes an identity of UE1, an identity of UE2, and an identity of UE 3.

The second network element may determine, according to the information indicating the terminal device group, which terminal devices to collect the measurement results of the QoS parameters of, or aggregate the measurement results of the QoS parameters of which terminal devices, thereby determining the aggregate information.

4. Trigger condition for transmitting aggregated information

The triggering condition for transmitting the aggregation information may include periodically feeding back the aggregation information, or feeding back the aggregation information while satisfying a preset condition.

For example, the preset conditions herein may include that the aggregate bit rate is greater than the subscribed maximum bit rate of the group of terminal devices, and/or that the statistical value of the transmission delays of the terminal devices in the group of terminal devices is greater than the first preset threshold, etc.

And the second network element feeds back the aggregation information according to the triggering condition of sending the aggregation information.

5. And the indication information indicates the measurement result of the QoS parameter of the feedback terminal equipment.

It can be appreciated that the measurement result indicated to be fed back by the indication information is a measurement result at the terminal device level.

6. And feeding back a condition indicating a condition to be satisfied by the measurement result of the QoS parameter of the feedback terminal equipment.

For example, the feedback condition may indicate that the terminal device with a transmission delay greater than the second preset threshold value feeds back a measurement result of the QoS parameter, or that the terminal device with a transmission delay less than the third preset threshold value feeds back a measurement result of the QoS parameter, or that the terminal device with a QoS flow bit rate greater than the preset bit rate feeds back a measurement result of the QoS parameter. Wherein the second preset threshold is greater than the third preset threshold.

In some embodiments, when the first request message only includes the indication information and does not include the feedback condition, the data of the terminal device group further includes a measurement result of QoS parameters of each terminal device in the terminal device group, that is, the second network element feeds back the measurement result of QoS parameters of all terminal devices in the terminal device group to the first network element.

In some embodiments, when the first request message includes the indication information and the feedback condition, the data of the terminal device group further includes a measurement result of the QoS parameter of at least one terminal device in the terminal device group, and the measurement result of the QoS parameter of the at least one terminal device satisfies the feedback condition, that is, the second network element feeds back the measurement result of the QoS parameter of the part of the terminal devices in the terminal device group to the first network element.

7. An application identifier for indicating a range of applications that collect measurement results of QoS parameters of the terminal device.

For example, when the terminal device in the terminal device group is a terminal device participating in the horizontal federal learning, the application identifier is an identifier of the application of the horizontal federal learning.

The second network element indicates the user plane network element to collect the measurement result of the QoS parameter of the terminal equipment according to the application identifier.

Step 410: the second network element sends the data of the terminal equipment group to the first network element.

For example, when the second network element is an NWDAF network element, the second network element sends an analysis notification message (nnwdaf_analysis description_notification) to the first network element, the message carrying data of the terminal device group. When the second network element is a PCF network element, the first request message may be an event open notification message (nnwdaf_ EventExposure Notify), which carries data of the group of terminal devices. It should be noted that, each communication between the first network element and the second network element needs to be forwarded through the NEF network element.

In one possible implementation, the second network element sends a second request message to the user plane network element, where the second request message is used to request data of the terminal device group, and the second network element receives the data of the terminal device group from the user plane network element.

Wherein the second request message may include content included in the first request message in addition to the type information associated with the aggregation information. For example, the first request message includes the 1-7 items of content described above, and the second request message includes the 2-7 items of content described above.

By adopting the implementation manner, the user plane network element completes the collection of the measurement results of the QoS parameters of the terminal equipment in the terminal equipment group, determines the data of the terminal equipment group according to the collected measurement results, for example, determines the aggregation information according to the parameter information related to the aggregation information, and determines the measurement results of the QoS parameters of the terminal equipment needing to be fed back according to the indication information and/or the feedback condition. The user plane network element sends the determined data of the terminal equipment group to the second network element, and the second network element sends the data of the terminal equipment group to the first network element.

For example, the terminal equipment group includes UE1, UE2 and UE3, and the user plane network element receives the second request message and collects the measurement result of the QoS parameter of UE1, the measurement result of the QoS parameter of UE2 and the measurement result of the QoS parameter of UE3 according to the second request message. Further, the user plane network element determines that the aggregation information includes an aggregation bit rate and a statistic value of transmission delay according to the parameter information associated with the aggregation information in the second request message, and then sums up the bit rates of the QoS flows corresponding to the UE2 and the UE3 according to the bit rate of the QoS flow corresponding to the UE1 as the aggregation bit rate of the terminal equipment group. The user plane network element also calculates a statistic value of the transmission delay of the terminal equipment group according to the actual transmission delay of the UE1, the actual transmission delay of the UE2, the actual transmission delay of the UE3, and the expected transmission delay of the UE1, the expected transmission delay of the UE2 and the expected transmission delay of the UE3 received from the second network element or configured in advance. The user plane network element sends data of the terminal equipment group to the second network element, wherein the data of the terminal equipment group comprises an aggregation bit rate of the terminal equipment group and a statistic value of transmission delay of the terminal equipment group. The measurement result of the QoS parameter of UE1 includes the bit rate of the QoS flow corresponding to UE1 and the actual transmission delay of UE1, the measurement result of the QoS parameter of UE2 includes the bit rate of the QoS flow corresponding to UE2 and the actual transmission delay of UE2, and the measurement result of the QoS parameter of UE3 includes the bit rate of the QoS flow corresponding to UE3 and the actual transmission delay of UE 3.

In one possible implementation, the second network element sends a third request message to the user plane network element, where the third request message is used to request a measurement result of a QoS parameter of a terminal device in the terminal device group, the second network element receives, from the user plane network element, the measurement result of the QoS parameter of the terminal device in the terminal device group, and the second network element determines data of the terminal device group according to the measurement result of the QoS parameter of the terminal device in the terminal device group and the first request message.

By adopting the implementation manner, the user plane network element completes the collection of the measurement results of the QoS parameters of the terminal equipment in the terminal equipment group and sends the collected measurement results to the second network element, and the second network element determines the data of the terminal equipment group according to the collected results, for example, determines the aggregation information according to the parameter information related to the aggregation information, and determines the measurement results of the QoS parameters of the terminal equipment needing to be fed back according to the indication information and/or the feedback condition.

For example, the terminal equipment group includes UE1, UE2 and UE3, and the user plane network element receives the third request message, and collects the measurement result of the QoS parameter of UE1, the measurement result of the QoS parameter of UE2 and the measurement result of the QoS parameter of UE3 according to the third request message. The user plane network element sends the measurement result of the QoS parameter of UE1, the measurement result of the QoS parameter of UE2, and the measurement result of the QoS parameter of UE3 to the second network element. And the second network element determines that the aggregation information comprises an aggregation bit rate and a statistic value of transmission delay according to the parameter information associated with the aggregation information in the first request message, and then sums up the bit rates of the QoS flows corresponding to the UE3 as the aggregation bit rate of the terminal equipment group according to the bit rate of the QoS flow corresponding to the UE1 and the bit rate of the QoS flow corresponding to the UE 2. The second network element also calculates a statistic value of the transmission delay of the terminal equipment group according to the actual transmission delay of the UE1, the actual transmission delay of the UE2, the actual transmission delay of the UE3, and the expected transmission delay of the UE1, the expected transmission delay of the UE2 and the expected transmission delay of the UE3 which are configured in advance. The second network element sends data of the terminal equipment group to the first network element, wherein the data of the terminal equipment group comprises an aggregation bit rate of the terminal equipment group and a statistic value of transmission delay of the terminal equipment group. The measurement result of the QoS parameter of UE1 includes the bit rate of the QoS flow corresponding to UE1 and the actual transmission delay of UE1, the measurement result of the QoS parameter of UE2 includes the bit rate of the QoS flow corresponding to UE2 and the actual transmission delay of UE2, and the measurement result of the QoS parameter of UE3 includes the bit rate of the QoS flow corresponding to UE3 and the actual transmission delay of UE 3.

Step 420: the first network element adjusts QoS parameters of the first terminal equipment in the terminal equipment group according to the data of the terminal equipment group.

It will be appreciated that the first network element may adjust QoS parameters of at least one terminal device in the group of terminal devices, e.g. QoS parameters of the first terminal device, or QoS parameters of a plurality of terminal devices, or QoS parameters of all terminal devices.

When the QoS parameters of the terminal device are adjusted, the first network element may adjust the value of the QoS parameters, or the value range of the QoS parameters. For example, the first network element may adjust the value of the bit rate of the QoS flow of the first terminal device, or the range of values of the bit rate.

Possible implementations of the adjustment of QoS parameters of at least one terminal device in a group of terminal devices are described below in connection with data of a specific group of terminal devices, wherein the at least one terminal device comprises a first terminal device.

Mode 1: when the aggregate information includes an aggregate bit rate, if the aggregate bit rate is greater than a subscribed maximum bit rate of the terminal equipment group, the first network element adjusts the bit rate of the QoS flow of the at least one terminal equipment, and after adjusting the bit rate of the QoS flow of the at least one terminal equipment, the sum of the bit rates of the QoS flows of the respective terminal equipment in the terminal equipment group is less than or equal to the subscribed maximum bit rate, or the sum of the lower bounds of the bit rate value ranges of the QoS flows of the respective terminal equipment in the terminal equipment group is less than or equal to the subscribed maximum bit rate.

In some possible embodiments, if the first request message includes a trigger condition for sending the aggregation information, and the trigger condition for sending the aggregation information includes that an aggregation bit rate of the terminal equipment group is greater than a subscription maximum bit rate of the terminal equipment group, the second network element or the user plane network element determines, according to the subscription maximum bit rate of the terminal equipment group, whether the aggregation bit rate is greater than the subscription maximum bit rate of the terminal equipment group, and if yes, the second network element sends data of the terminal equipment group to the first network element, where the data of the terminal equipment group includes statistics of transmission delay.

In some possible embodiments, if the first request message does not include a trigger condition for sending the aggregation information, the first network element determines, or according to the subscription maximum bitrate of the terminal device group, whether the aggregation bitrate is greater than the subscription maximum bitrate of the terminal device group.

In some possible embodiments, when the first network element adjusts the bit rate of the QoS flow of the at least one terminal device, the first network element may determine an adjustment scheme according to the bit rate of the QoS flow configured for each terminal device in the terminal device group last time, i.e. adjust the bit rates of the QoS flows of which terminal devices, and the direction and the size of the adjustment, so that after adjusting the bit rate of the QoS flow of the at least one terminal device, the sum of the bit rates of the QoS flows of the respective terminal devices in the terminal device group is less than or equal to the subscription maximum bit rate, or the sum of the lower bounds of the bit rate range of the QoS flows of the respective terminal devices in the terminal device group is less than or equal to the subscription maximum bit rate.

In some possible embodiments, when the first network element adjusts the bit rate of the QoS flow of at least one terminal device, if the first request message includes the indication information, the second network element further feeds back to the first network element a measurement result of the QoS parameter of each terminal device in the terminal device group, and the first network element may determine an adjustment scheme in combination with the measurement result of the QoS parameter of each terminal device in the terminal device group; or when the first network element adjusts the bit rate of the QoS flow of at least one terminal device, if the first request message includes the indication information and the feedback condition, the second network element further feeds back the measurement result of the QoS parameter of the terminal device that satisfies the feedback condition in the terminal device group to the first network element, and the first network element may determine the adjustment scheme in combination with the measurement result of the QoS parameter of the terminal device that satisfies the feedback condition in the terminal device group. For example, the feedback condition may be a measurement result of the feedback QoS parameter for the terminal device whose QoS flow bit rate is greater than the preset bit rate.

For example, the terminal equipment group includes UE1, UE2 and UE3, where the aggregate bit rate of the terminal equipment group is the sum of the bit rate of the QoS flow corresponding to UE1, the bit rate of the QoS flow corresponding to UE2 and the bit rate of the QoS flow corresponding to UE 3. When the aggregate bit rate of the terminal device group is greater than the subscribed maximum bit rate of the terminal device group, the first network element may adjust the value of at least one UE of UE1, UE2, and/or UE3, so that the bit rate of the QoS flow corresponding to UE1, the bit rate of the QoS flow corresponding to UE2, the sum of the bit rates of the QoS flows corresponding to UE3 is less than or equal to the subscribed maximum bit rate of the terminal device group, or the lower bound of the value range of the bit rate of the QoS flow corresponding to UE1, the lower bound of the value range of the bit rate of the QoS flow corresponding to UE2, and the sum of the lower bound of the value range of the bit rate of the QoS flow corresponding to UE3 is less than or equal to the subscribed maximum bit rate of the terminal device group.

Mode 2: when the aggregate information includes statistics of transmission delays of terminal devices in the terminal device group, if the statistics of the transmission delays are greater than a first preset threshold, the first network element adjusts a bit rate of a QoS flow of at least one terminal device according to data of the terminal device group.

The at least one terminal device is, for example, a terminal device whose transmission delay is greater than a second preset threshold or less than a third preset threshold, wherein the second preset threshold is greater than the third preset threshold.

Further, similarly to mode 1, after adjusting the bit rate of the QoS stream of at least one terminal device, the sum of the bit rates of the QoS streams of the respective terminal devices in the terminal device group is smaller than or equal to the subscription maximum bit rate, or the sum of the lower bounds of the value ranges of the bit rates of the QoS streams of the respective terminal devices in the terminal device group is smaller than or equal to the subscription maximum bit rate.

In some possible embodiments, if the first request message includes a trigger condition for sending the aggregation information, and the trigger condition for sending the aggregation information includes that the statistical value of the transmission delay is greater than a first preset threshold, the second network element or the user plane network element determines, according to the first preset threshold, whether the statistical value of the transmission delay is greater than the first preset threshold, and if yes, the second network element sends data of the terminal device group to the first network element, where the data of the terminal device group includes the statistical value of the transmission delay. In some possible embodiments, if the first request message does not include a trigger condition for sending the aggregation information, the first network element determines, according to a first preset threshold, whether the statistical value of the transmission delay is greater than the first preset threshold.

In some possible embodiments, when the first network element adjusts the bit rate of the QoS flow of at least one terminal device, if the first request message includes the indication information, the second network element further feeds back to the first network element the measurement result of the QoS parameter of each terminal device in the terminal device group, and the first network element may determine the adjustment scheme, that is, adjust the bit rate of the QoS flow of which terminal devices, and the direction and the size of the adjustment, in combination with the measurement result of the QoS parameter of each terminal device in the terminal device group. Illustratively, the transmission delay is reduced by adjusting the bit rate for a terminal device with a longer transmission delay (e.g., a terminal device with a transmission delay greater than a second preset threshold) and/or the transmission delay is increased by adjusting the bit rate for a terminal device with a shorter transmission delay (e.g., a terminal device with a transmission delay less than a third preset threshold).

Or when the first network element adjusts the bit rate of the QoS flow of at least one terminal device, if the first request message includes the indication information and the feedback condition, the second network element further feeds back the measurement result of the QoS parameter of the terminal device that satisfies the feedback condition in the terminal device group to the first network element, and the first network element may determine the adjustment scheme in combination with the measurement result of the QoS parameter of the terminal device that satisfies the feedback condition in the terminal device group. For example, the feedback condition is a measurement result of the feedback QoS parameter of the terminal device with the transmission delay of the terminal device being greater than the second preset threshold, and/or a measurement result of the feedback QoS parameter of the terminal device with the transmission delay of the terminal device being less than the third preset threshold.

Illustratively, as shown in fig. 5A, assuming that the variance determined by the weighted transmission delay of UE1, the weighted transmission delay of UE2, and the weighted transmission delay of UE3 or the variance determined by the differential transmission delay of UE1, the differential transmission delay of UE2, and the differential transmission delay of UE3 is greater than a first preset threshold, the first network element decreases the bit rate of the QoS flow of UE1, increases the actual transmission delay of UE1, increases the bit rate of the QoS flow of UE2, shortens the actual transmission delay of UE2, decreases the bit rate of the QoS flow of UE3, and increases the actual transmission delay of UE 3. As shown in fig. 5B, for each UE, the duration from the triangle mark to the hollow circle mark is the actual transmission delay before adjustment of the UE, the duration from the triangle mark to the solid circle mark is the adjusted actual transmission delay of the UE, the duration from the triangle mark to the intersection of the first dotted line and the time axis is the adjusted expected transmission delay of the UE, and the duration from the triangle mark to the intersection of the second dotted line and the time axis is the expected transmission delay before adjustment of the UE. It can be seen that after the first network element adjusts the bit rate of UE1, the bit rate of UE2 and the bit rate of UE3, the times when the QoS flows corresponding to UE1, UE2 and UE3 respectively reach the server are approximately the same and are relatively close. Further, before the adjustment, the server receives the calculation results of all the UEs in the terminal device group at the time indicated by the second dotted line, and after the adjustment, the server receives the calculation results of all the UEs in the terminal device group at the time indicated by the first dotted line, wherein the time indicated by the first dotted line is earlier than the time indicated by the second dotted line, so that the waiting time of the server can be reduced, and further the model training efficiency can be improved.

Step 430: the first network element sends the adjusted QoS parameters of the first terminal equipment to the strategy control network element.

In addition, the policy control network element performs corresponding policy control according to the aggregation information of the terminal device group, so as to ensure that the limitation of the aggregation information is met, for example, the aggregation bit rate needs to be less than or equal to the subscription maximum bit rate of the terminal device group, and the statistical value of the transmission delay needs to be less than or equal to a first preset threshold. The following briefly describes the related strategy control method, taking the aggregate bit rate as an example.

Illustratively, the policy control method includes:

1. upon establishing a session management (session management, SM) policy association, the policy control network element checks whether the aggregate bit rate of the group of terminal devices is higher than the subscribed maximum bit rate of the group of terminal devices. If yes, the policy control network element shall refuse to establish the SM policy association, otherwise, the policy control network element normally establishes the SM policy association.

2. When the aggregate bit rate of the terminal equipment group is smaller than the subscription maximum bit rate of the terminal equipment group, and meanwhile, the aggregate bit rate of the terminal equipment group is larger than a preset threshold, the policy control network element can limit the flow of the protocol data unit (protocol data unit, PDU) session or PCC rule through a policy control method and perform corresponding interaction with the session management network element, wherein the preset threshold is smaller than the subscription maximum bit rate of the terminal equipment group, and the preset threshold is close to the subscription maximum bit rate of the terminal equipment group, for example, the preset threshold is 95% of the subscription maximum bit rate of the terminal equipment group; if the policy control network element finds that the aggregate bit rate of the group of terminal devices is less than the preset threshold, the policy control network element may relax the flow restriction of the PDU session or PCC rule.

By adopting the embodiment, the first network element subscribes the data of the terminal equipment group to the second network element, the second network element sends the data of the terminal equipment group to the first network element, and the first network element adjusts the QoS parameter of at least one terminal equipment in the terminal equipment group according to the data of the terminal equipment group, so that the model training efficiency can be improved.

In addition, the first network element may also perform the operational flow shown in fig. 6 before the first network element sends the first request message to the second network element.

Step 600: the first network element sends the subscription maximum bit rate of the terminal equipment group to a third network element, and the third network element is a unified data storage network element or a unified data management network element.

The first network element may determine a subscription maximum bitrate of the terminal device group according to model training traffic requirements of the lateral federal learning, and send the subscription maximum bitrate of the terminal device group to the third network element. The subscribed maximum bit rate of the terminal device group may be carried by a data management creation Request (nudr_dm_create Request) or a data management Update Request (nudr_dm_update Request).

When the subscription maximum bit rate of the terminal equipment group is carried by the nudr_dm_create Request, the third network element creates the subscription maximum bit rate of the terminal equipment group in subscription information, and sends a data management creation Response (nudr_dm_create Response) to the first network element, the message indicating that the subscription information has been created.

When the subscription maximum bit rate of the terminal equipment group is carried by the nudr_dm_update Request, the third network element updates the subscription maximum bit rate of the terminal equipment group in subscription information, and sends a data management Update Response (nudr_dm_update Response) to the first network element, wherein the message indicates that the subscription information is updated.

Step 610: the first network element sends first information to the policy control function, wherein the first information comprises reference information of QoS parameters corresponding to each terminal device included in the terminal device group.

The reference information of the QoS parameters respectively corresponding to each terminal device included in the terminal device group includes at least one of the following:

the bit rate of each QoS stream or the value range of each terminal equipment included in the terminal equipment group is respectively corresponding to the bit rate, or the value of the packet loss rate or the value range of each terminal equipment included in the terminal equipment group is respectively corresponding to the packet loss rate, or the value of the transmission delay or the value range of each terminal equipment included in the terminal equipment group is respectively corresponding to the terminal equipment.

For example, for a certain terminal device, the bit rate of QoS flow=20 Mbps, packet loss rate=0.01%. Alternatively, the bit rate of 10Mbps < qos flows is <20Mbps, and the packet loss rate is <0.01%.

Illustratively, the first network element may determine the first information according to model training traffic requirements of the lateral federal learning, and the first information may be carried by a policy authorization creation Request (npcf_policy authorization_create Request) or a policy authorization Update Request (npcf_policy authorization_update Request).

Step 620: the policy control network element requests the third network element for the subscribed maximum bit rate of the terminal equipment group.

Illustratively, the policy control network element requests the subscribed maximum bit rate of the group of terminal devices from the third network element through a data management Query Request (nudr_dm_query Request) service operation.

Step 630: and the third network element sends the signed maximum bit rate of the terminal equipment group to the strategy control network element.

The third network element sends the subscribed maximum bit rate of the terminal device group to the policy control network element via a data management Query Response (nudr_dm_query Response) service operation, for example.

Step 640: and the strategy control network element verifies the first information according to the subscription maximum bit rate of the terminal equipment group.

In an exemplary embodiment, when the first information includes a value of a bit rate of a QoS flow corresponding to each terminal device included in the terminal device group, the policy control network element determines, according to a subscription maximum bit rate of the terminal device group and a value of a bit rate of a QoS flow corresponding to each terminal device included in the terminal device group, whether a sum of bit rates of QoS flows corresponding to each terminal device included in the terminal device group is less than or equal to the subscription maximum bit rate of the terminal device group, if yes, verification is successful, otherwise verification fails.

Or when the first information comprises the value ranges of the bit rates of the QoS flows respectively corresponding to the terminal equipment included in the terminal equipment group, the policy control network element determines whether the sum of the lower bounds of the value ranges of the bit rates of the QoS flows respectively corresponding to the terminal equipment included in the terminal equipment group is smaller than or equal to the subscription maximum bit rate of the terminal equipment group according to the subscription maximum bit rate of the terminal equipment group and the value ranges of the bit rates of the QoS flows respectively corresponding to the terminal equipment included in the terminal equipment group, if so, the verification is successful, otherwise, the verification is failed.

Step 650: and when the verification is successful, the policy control network element generates policy and charging control (policy and charging control, PCC) rules respectively corresponding to each terminal device included in the terminal device group according to the first information, and the second network element sends the PCC rules respectively corresponding to each terminal device to the session management network element.

Further, the session management network element may establish or modify a corresponding session according to PCC rules corresponding to each terminal device sent by the policy control network element.

Step 660: the policy control network element sends second information to the first network element, wherein the second information indicates that corresponding PCC rules are generated for each terminal device included in the terminal device group.

For example, when the first information is carried by the npcf_policy authorization_create Request, the second information may be carried by a policy authorization creation Response (npcf_policy authorization_create Response).

When the first information is carried by the npcf_policy authorization_update Request, the second information may be carried by a policy authorization Update Response (npcf_policy authorization_update Response).

In addition, in order to realize adjustment of QoS parameters of different participants, the efficiency of model training of federal learning is improved. The present application provides a further communication method, as shown in fig. 7, where the following first network element may be an application function network element. In the embodiment shown in fig. 7, the first network element subscribes the data of the terminal device group to the data analysis function network element, and provides address information of the policy control network element, and the second network element feeds back the data of the terminal device group to the policy control network element. And the strategy control network element adjusts the QoS parameters of the first terminal equipment in the terminal equipment group according to the data of the terminal equipment group. In contrast to the embodiment shown in fig. 4, the first network element is responsible for receiving the data of the terminal device group and adjusting the QoS parameters of the first terminal device in the terminal device group according to the data of the terminal device group, and in the embodiment shown in fig. 7, the policy control network element is responsible for receiving the data of the terminal device group and adjusting the QoS parameters of the first terminal device in the terminal device group according to the data of the terminal device group.

Specifically, the method comprises the following steps:

step 700: the first network element sends a first request message to the data analysis function network element, wherein the first request message is used for requesting data of a terminal equipment group, and the data of the terminal equipment group comprises aggregation information of measurement results of QoS parameters.

Step 700 may refer to the related description in step 400, and will not be described herein.

It should be noted that, the first request message may include address information of the policy control network element in addition to the content of items 1 to 8.

Step 710: the data analysis function network element sends the data of the terminal equipment group to the strategy control network element according to the address information of the strategy control network element.

The specific implementation of the data analysis function network element in determining the data of the terminal device group may refer to the related description in step 410.

Step 720: the strategy control network element receives information of the terminal equipment group, and adjusts QoS parameters of a first terminal equipment in the terminal equipment group according to data of the terminal equipment group.

The policy control network element adjusts the specific implementation manner of the QoS parameter of the first terminal device in the terminal device group according to the data of the terminal device group, and may refer to the specific implementation manner of the QoS parameter of the first terminal device in the terminal device group adjusted by the first network element according to the data of the terminal device group in step 420.

By adopting the embodiment, the first network element subscribes the data of the terminal equipment group to the data analysis function network element, and notifies the second network element to send the data of the terminal equipment group to the strategy control network element, and the strategy control network element adjusts the QoS parameter of at least one terminal equipment in the terminal equipment group according to the data of the terminal equipment group, so that the efficiency of model training of federal learning can be improved.

It will be appreciated that the first network element may also perform the operational procedure shown in fig. 6 prior to performing step 700.

The present application provides a further communication method, as shown in fig. 8, where the following first network element may be an application function network element. In the embodiment shown in fig. 8, the first network element subscribes the data of the terminal equipment group to the policy control network element, and the policy control network element obtains the data of the terminal equipment group, and adjusts the QoS parameters of the first terminal equipment in the terminal equipment group according to the data of the terminal equipment group. Therefore, compared to the embodiment shown in fig. 4, in which the first network element is responsible for receiving the data of the terminal device group and adjusting the QoS parameters of the first terminal device in the terminal device group according to the data of the terminal device group, in the embodiment shown in fig. 8, the policy control network element is responsible for obtaining the data of the terminal device group and adjusting the QoS parameters of the first terminal device in the terminal device group according to the data of the terminal device group.

The method comprises the following steps:

step 800: the first network element sends a first request message to the policy control network element, where the first request message is used to request data of a terminal equipment group, and the data of the terminal equipment group includes aggregation information of measurement results of QoS parameters.

Step 800 may refer to the related description in step 400, which is not described herein.

Step 810: the policy control network element determines data of the group of terminal devices.

The specific implementation manner of determining the data of the terminal device group by the policy control network element may refer to the description related to the data of the second network element determination terminal device group in step 410.

Step 820: and the strategy control network element adjusts the QoS parameters of the first terminal equipment in the terminal equipment group according to the data of the terminal equipment group.

By adopting the embodiment, the first network element subscribes the data of the terminal equipment group to the strategy control network element, the strategy control network element acquires the data of the terminal equipment group, and the QoS parameter of at least one terminal equipment in the terminal equipment group is adjusted according to the data of the terminal equipment group, so that the model training efficiency can be improved.

It will be appreciated that the first network element may also perform the operational procedure shown in fig. 6 prior to performing step 800.

The application provides a communication method. The difference is different from the above embodiment, the application function network element may collect data without NWDAF or PCF, but rather, count or acquire the transmission delay and the local computation delay of each terminal device in the terminal device group, so as to determine the adjustment policy of the QoS parameters of the terminal devices in the terminal device group, reduce the number of messages interacted between network elements, reduce the load of network elements, and improve the QoS parameter adjustment efficiency of the terminal devices, so that the sum of the local computation delay and the transmission delay of different terminal devices is approximately the same, thereby improving the model training efficiency of transverse federal learning.

As shown in fig. 9, the method includes:

step 900: the application function network element obtains the transmission delay and the local calculation delay of each terminal device in the terminal device group, wherein the terminal devices in the terminal device group are terminal devices participating in transverse federal learning.

Wherein the local computation delay is a length of time required to determine updated parameters of the model of the lateral federal learning. The transmission delay is the length of time required to transmit the update parameters to the application function network element. It will be appreciated that the local computation delays may vary from one terminal device to another in the group of terminal devices, as may the transmission delays of the different terminal devices. As shown in fig. 5A, the terminal device group includes UE1, UE2, and UE3, each UE corresponds to a time axis, and a duration from a start point of the time axis (i.e., a local calculation start time) to a triangle mark corresponds to a local calculation completion time of the UE, i.e., a local calculation delay, and a duration from the triangle mark to a circle mark corresponds to a transmission delay of the UE. Wherein the local calculation start time is a start time for determining update parameters of the model of the lateral federation learning.

For example, the application function network element may determine the transmission delay of the terminal device that transmits the data packet according to the transmission time of the data packet carrying the update parameter and the reception time of the data packet. Reference may be made in particular to the relevant description in fig. 10.

For example, the application function network element may acquire the local computation delay of the terminal device participating in the horizontal federal learning before the horizontal federal learning starts, or acquire the local computation delay of the terminal device participating in the horizontal federal learning in a model training phase of the horizontal federal learning. Reference may be made in particular to the relevant description in fig. 10.

Step 910: and the application function network element adjusts the QoS parameters of the first terminal equipment in the terminal equipment group according to the transmission delay and the local calculation delay of each terminal equipment.

In an exemplary embodiment, when the application function network element adjusts QoS parameters of a first terminal device in the terminal device group according to the transmission delay and the local computation delay of each terminal device, the application function network element determines a statistic value of total delay of each terminal device according to the transmission delay and the local computation delay of each terminal device, where the total delay of each terminal device is a sum of the transmission delay and the local computation delay of the terminal device. And under the condition that the total time delay of the first terminal equipment is larger than a first preset threshold value or smaller than a second preset threshold value, the application function network element adjusts the QoS parameters of the first terminal equipment, wherein the first preset threshold value and the second preset threshold value are determined according to the statistical value.

The statistical value may be an arithmetic average value, a geometric average value, a root mean square average value, a harmonic average value, a weighted average value or the like, which is not limited in the present application.

Wherein the first preset threshold and the second preset threshold are determined by the application function network element. For example, the first preset threshold may be a statistical value of the total delay +20ms, or a statistical value of the total delay 1.12, etc. For another example, the second preset threshold may be a statistical value of the total delay of-20 ms, or a statistical value of the total delay of 0.88, etc.

Wherein the adjusted QoS parameter of the first terminal device includes at least one of a resource type, a priority, a packet delay budget, a guaranteed stream bit rate, a maximum stream bit rate, an allocation and a preemption priority.

Illustratively, the resource types may include GBR, non-GBR, delay-critical (GBR). By adjusting the type of the QoS flow of the first terminal device from Non-GBR to GBR or delay critical GBR, the network can be ensured to reserve enough resources for the QoS flow of the first terminal device to ensure the bandwidth of the QoS flow, and the probability that the set transmission delay is ensured is further improved.

By way of example, priority may refer to the priority of resource scheduling, i.e., a priority level (priority level) parameter in 5 QI. Allocation and preemption priorities refer to the priorities of resource allocation and preemption. By adjusting the priority or allocation and preemption priority of the QoS flows of the first terminal device, it is possible to ensure that the network will prioritize the priority or allocate and preemption priority QoS flows under the congestion scenario, so that under the condition that network resources are limited, the priority or allocation and preemption priority of the QoS flows is increased to improve the probability that the set transmission delay is guaranteed.

Illustratively, by lowering the packet delay budget, the transmission delay of the QoS flow of the first terminal device may be reduced, and by raising the Bao Shiyan budget, the transmission delay of the QoS flow of the first terminal device may be increased.

Illustratively, the stability of the QoS Flow bit rate and thus the stability of the delay can be ensured by adjusting the guaranteed Flow bit rate and the maximum Flow bit rate.

In addition, the application function network element can also adjust parameters such as packet error rate, average window, maximum data burst quantity and the like.

Step 920: the application function network element sends the adjusted QoS parameters of the first terminal equipment to the strategy control network element.

In addition, in a possible implementation manner, the application function network element adjusts the QoS reference of the first terminal device in the terminal device group according to the transmission delay and the local computation delay of each terminal device. Wherein the QoS reference does not specify a specific QoS parameter, mapped to the specific QoS parameter by the policy control network element. That is, the policy control network element may adjust QoS parameters of the first terminal device in the terminal device group according to the QoS reference of the first terminal device. At this time, the application function network element sends the adjusted QoS reference of the first terminal device to the policy control network element.

For example, the application function network element sends the adjusted expected transmission delay of the first terminal device to the policy control network element, and the policy control network element maps the adjusted expected transmission delay of the first terminal device to specific QoS parameters, for example, at least one of a resource type, a priority, a packet delay budget, a guaranteed stream bit rate, a maximum stream bit rate, an allocation and a preemption priority.

The embodiment shown in fig. 9 is described below with reference to fig. 10:

in this embodiment, before the model training stage of the horizontal federal learning, the application function network element may set different expected transmission delays for each terminal device according to the local computation delays of the terminal devices participating in the horizontal federal learning, so that the sum of the local computation delays and the expected transmission delays of the different terminal devices is approximately the same, so as to improve the model training efficiency of the horizontal federal learning. In the model training stage of the horizontal federal learning, the application function network element can obtain the sum of the local calculation time delay and the actual transmission time delay of different terminal devices, namely the total time delay. Furthermore, the application function network element can calculate the statistics value of the total time delay of different terminal devices, namely the expected total time delay, and screen out the terminal devices with larger total time delay and expected total time delay, and the total time delay of the terminal devices can be approximately the same as the expected total time delay by adjusting the QoS parameters of the terminal devices.

S1001.AF obtains the expected transmission delay of each UE according to the local calculation delay and the initial total delay of each UE in the terminal equipment group, and sets the QoS reference value or QoS parameter value of the QoS Flow of each UE aiming at the federal learning service according to the expected transmission delay.

The AF can acquire the local calculation time delay and the initial total time delay of the UE participating in the transverse federal learning in a test stage. The test stage is to determine the UE participating in the transverse federal learning at the AF, establish session connection with the UE participating in the transverse federal learning, and execute model training of the transverse federal learning at the AF and the UE. Furthermore, the test phase may also be referred to as a preparation phase. In the test stage, the AF interacts with the UE through the application layer data packet, so that the local calculation time delay and the initial total time delay of the UE can be obtained, and further the local calculation time delay and the initial total time delay of each UE participating in the transverse federal learning are obtained.

Illustratively, in order to achieve that the sum of the local computation delays and the transmission delays of different UEs is approximately the same, the AF may set a deadline by which intermediate results (i.e. updated parameters) of the UEs all reach the AF. Furthermore, the AF may calculate the expected transmission delay of different UEs according to the deadline and the local computation delay of each UE, and set the QoS reference value or QoS parameter value of the QoS Flow of each UE, for example, the PDB, according to the expected transmission delay of each UE.

For example, the terminal device group includes UE1, UE2, and UE3, where the local calculated delay of UE1 is 20ms, the total delay of UE1 is 90ms, the local calculated delay of UE2 is 40ms, the total delay of UE2 is 70ms, the local calculated delay of UE3 is 30ms, and the total delay of UE3 is 80ms. The AF sets the cut-off time according to the 3 total time delays, if the AF calculates the average value of the 3 total time delays to be 80ms, the cut-off time is set to be 80ms, namely, the required time is 80ms from the local calculation starting time to the reception of the data packets of all the UE. The expected transmission delay of UE1 is 60ms, the expected transmission delay of UE2 is 40ms, and the expected transmission delay of UE3 is 50ms. AF sets the PDB of the QoS Flow of UE1 according to the expected transmission delay of UE 1. AF sets the PDB of the QoS Flow of UE2 according to the expected transmission delay of UE2, and AF sets the PDB of the QoS Flow of UE3 according to the expected transmission delay of UE 3. For example, PDB of QoS Flow of UE2 < PDB of QoS Flow of UE3 < PDB of QoS Flow of UE 1.

S1002. the af sends a request message to the PCF, the request message including a QoS reference value or a QoS parameter value.

Illustratively, the AF sends the QoS reference value or QoS parameter value of each UE in the terminal device group to the PCF through a PCF serving interface policy authorization creation Request (npcf_policy authorization_creation Request), or the AF sends the QoS reference value or QoS parameter value of the QoS parameter of each UE in the terminal device group to the PCF through a PCF serving interface policy authorization Update Request (npcf_policy authorization_update Request).

Wherein the request message includes a UE identification (UE ID), an application session identification (App session ID), a QoS reference or a QoS parameter (QoS reference or QoS parameters), wherein the UE identification is used to indicate the UE to which the QoS parameter is adapted. An application session identification (App session ID) for indicating QoS parameters of a session of the adapted application. The QoS reference or QoS parameter indicates an adjusted QoS parameter, e.g., qoS reference is terminal equipment transmission delay and QoS parameter is PDB.

S1003.PCF sets up the corresponding QoS parameter according to the request message, and produces PCC rule.

S1004. the pcf sends the PCC rules to the SMF to bind the PCC rules to the corresponding QoS flows by the SMF.

The pcf sends a response message to the AF. The response message indicates that the QoS parameter setting was successful.

Illustratively, when the AF sends the PCF a QoS reference value or QoS parameter value for each UE in the group of terminal devices through the PCF service interface policy authorization creation request, the PCF notifies the AF of the success of QoS parameter setting through the PCF service interface policy authorization creation Response (npcf_policy_creation Response). Or, when the AF sends the PCF a QoS reference value or a QoS parameter value of the QoS parameter of each UE in the terminal equipment group through the PCF service interface policy authorization Update request, the PCF notifies the AF of the success of QoS parameter setting through the PCF service interface policy authorization Update Response (npcf_policy Update Response).

In addition, in some embodiments, the PCF may also notify the AF of QoS parameter setting failure, e.g., insufficient network resources, failure to meet the QoS parameters specified by the AF, etc.

After S1005, after the QoS parameter setting of the transverse federal learning QoS Flow of the terminal device is completed, the AF performs model training of transverse federal learning with each UE in the terminal device group.

And S1006, the AF acquires the transmission delay and the local calculation delay of each UE in the terminal equipment group.

In one possible design, when the UE sends the data packet to the AF, the sending time of the data packet is carried as a time stamp in the data packet, and after the AF receives the data packet, the AF can calculate the transmission delay of the data packet according to the receiving time of the data packet and the time stamp. The data packet carries updated parameters of a model of the horizontal federation learning. For example, the transmission delay of each UE acquired by the AF may refer to an average value of transmission delays of all data packets of a certain training round. For example, the UE transmits 10 data packets in total in a certain training round, and the AF determines the transmission delay of each data packet according to the above method, and further determines the average value of the transmission delays of the 10 data packets as the transmission delay of the UE.

In one possible design, the AF may obtain the local computation delay of the UE during the test phase.

In one possible design, when the UE sends a data packet to the AF, the sending time of the data packet is carried as a time stamp in the data packet, and after the AF receives the data packet, the AF may determine the local computation delay of the UE according to the time stamp and the local computation start time. The data packet carries updated parameters of a model of the horizontal federation learning. Illustratively, the locally calculated delay of each UE that the AF may obtain may refer to an average of locally calculated delays of all data packets of a certain training round. It will be appreciated that the local computation start time for each UE participating in the lateral federal learning is approximately the same.

And S1007.AF adjusts the QoS reference value or QoS parameter value of the UE1 in the terminal equipment group according to the transmission delay and the local calculation delay of each UE.

AF calculates the sum of the transmission delay and the local calculation delay of each UE as the total delay of the UE, and then determines the statistic value of the total delay of each UE, namely the expected total delay, according to the total delay of each UE. The statistical value of the total delay of each UE may be an arithmetic average, a geometric average, a root mean square average, a harmonic average, a weighted average of the total delay of each UE.

Further, in case the total delay of UE1 is greater than the first preset threshold or less than the second preset threshold, the AF adjusts the QoS reference value or QoS parameter value of UE 1.

For example, assuming that the statistics value is an arithmetic average value, the AF determines that the arithmetic average value of the total delay of each UE is 50ms, the AF sets a first preset threshold value to be the arithmetic average value +10ms, that is, 60ms, and sets a second preset threshold value to be the arithmetic average value-10 ms, that is, 40ms, the AF screens out UEs with a total delay less than 40ms and UEs with a total delay greater than 60ms, and adjusts QoS reference values or QoS parameter values of the UEs.

For example, for a UE with a total latency of less than 40ms, the AF may turn up the PDB corresponding to the UE and/or turn down the ARP of the QoS Flow for the UE.

For another example, for a UE with a total delay greater than 60ms, the AF may turn down the PDB corresponding to the UE and/or turn up the ARP of the QoS Flow for the UE. The probability of ensuring the set expected transmission delay can be improved by increasing the ARP of the QoS Flow of the UE. In addition, the AF can set the GBR and/or MBR and other QoS parameters of the QoS Flow to ensure the stability of the bit rate of the QoS Flow, thereby ensuring the stability of time delay. GBR may be GFBR and MBR may be MFBR.

The af sends a request message to the PCF requesting adjustment of the QoS parameters of UE 1.

Illustratively, the AF sends the adjusted QoS reference value or QoS parameter value of UE1 to the PCF through the PCF service interface policy authorization Update Request (Npcf.

The request message includes UE1 ID, app session ID, adjusted QoS reference value or QoS parameter value.

S1009. the pcf sets the corresponding QoS parameters according to the request message and generates PCC rules.

In addition, the PCF updates the corresponding QoS parameters based on the request message. Furthermore, in some possible embodiments, the PCF may change the type of QoS Flow from Non-GBR to GBR or Delay-critical GBR and generate updated PCC rules. For example, only QoS flows of GBR and Delay-critical GBR types have GBR and/or MBR parameters, so if AF specifies values of GBR and/or MBR, or AF sets a reference value of stream bit rate, it means that if the type of QoS Flow was Non-GBR before, PCF will change the type of QoS Flow to GBR or Delay-critical GBR.

And S1010. The PCF sends the updated PCC rule to the SMF so that the SMF binds the updated PCC rule to the corresponding QoS Flow.

And S1011. The PCF sends a response message to the AF. The response message indicates that the QoS parameter setting was successful.

Illustratively, the PCF informs the AF of the QoS parameter setting success through PCF server interface policy authorization update response (npcf_ PolicyAuthorizationUpdate Response) service operation.

By adopting the method, when the QoS parameter adjustment strategy of the terminal equipment is determined, the application function network element does not need to rely on the NWDAF or PCF network element to acquire the data of the terminal equipment from the UPF, so that the burden of other network elements (such as NWDAF, PCF, UPF) can be reduced, and the QoS parameter adjustment efficiency of the terminal equipment is improved.

Fig. 11 shows a possible exemplary block diagram of a communication device according to an embodiment of the present application, the device 1100 comprising: the transceiver module 1120 and the processing module 1110, the transceiver module 1120 may include a receiving unit and a transmitting unit. The processing module 1110 is configured to control and manage the operations of the apparatus 1100. The transceiver module 1120 is used to support communication of the apparatus 1100 with other network entities. Optionally, the apparatus 1100 may further comprise a storage unit for storing program code and data of the apparatus 1100.

Alternatively, the various modules in the apparatus 1100 may be implemented in software.

Alternatively, the processing module 1110 may be a processor or controller, such as a general purpose central processing unit (central processing unit, CPU), a general purpose processor, digital signal processing (digital signal processing, DSP), application specific integrated circuit (application specific integrated circuits, ASIC), field programmable gate array (field programmable gate array, FPGA) or other programmable logic device, transistor logic device, hardware components, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules and circuits described in connection with the disclosure of embodiments of the present application. The processor may also be a combination that performs the function of a computation, e.g., a combination comprising one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The transceiver module 1120 may be a communication interface, a transceiver circuit, or the like, where the communication interface is generally called, and in a specific implementation, the communication interface may include multiple interfaces, and the storage unit may be a memory.

When the apparatus 1100 is a first network element or a chip in a first network element, the processing module 1110 in the apparatus 1100 may support the apparatus 1100 to perform the actions of the first network element in the method examples above, for example, may support the apparatus 1100 to perform the step 400 or the step 420 in fig. 4.

The transceiver module 1120 may support the apparatus 1100 to communicate with a second network element, e.g., the transceiver module 1120 may support the apparatus 1100 to perform steps 400, 410, 430 in fig. 4.

For example, the transceiver module 1120 is configured to send a first request message to a second network element, where the first request message is used to request data of a terminal device group, where terminal devices in the terminal device group are terminal devices that participate in horizontal federal learning; receiving data of the terminal equipment group from the second network element, wherein the data of the terminal equipment group comprises aggregation information of measurement results of QoS parameters; the processing module 1110 is configured to adjust QoS parameters of a first terminal device in the terminal device group according to data of the terminal device group; the transceiver module 1120 is configured to send the adjusted QoS parameter of the first terminal device to a policy control network element.

In one possible design, the aggregation information includes an aggregate bit rate that characterizes a sum of bit rates of QoS flows of terminal devices in the group of terminal devices; the processing module 1110 is configured to adjust, when adjusting the QoS parameter of a first terminal device in the terminal device group according to the data of the terminal device group, if the aggregate bit rate is greater than the subscribed maximum bit rate of the terminal device group, the bit rate of the QoS flow of the first terminal device according to the data of the terminal device group.

In one possible design, the aggregation information includes statistics of transmission delays of terminal devices in the group of terminal devices; the processing module 1110 is configured to adjust, when adjusting QoS parameters of a first terminal device in the terminal device group according to data of the terminal device group, if the statistical value of the transmission delay is greater than a first preset threshold, the bit rate of the QoS flow of the first terminal device according to the data of the terminal device group.

It should be understood that the apparatus 1100 according to the embodiment of the present application may correspond to the first network element in the foregoing method embodiment, and the operations and/or functions of each module in the apparatus 1100 are respectively for implementing the corresponding steps of the method of the first network element in the foregoing method embodiment, so that the beneficial effects in the foregoing method embodiment may also be implemented, which is not repeated herein for brevity.

When the apparatus 1100 is a second network element or a chip in a second network element, the processing module 1110 in the apparatus 1100 may support the apparatus 1100 to perform the actions of the second network element in the method examples above.

The transceiver module 1120 may support the apparatus 1100 to communicate with the first network element, for example, the transceiver module 1120 may support the apparatus 1100 to perform steps 400, 410, 430 in fig. 4.

For example, the processing module 1110 invokes the transceiver module 1120 to perform: receiving a first request message from a first network element, wherein the first request message is used for requesting data of a terminal equipment group, and the terminal equipment in the terminal equipment group is terminal equipment participating in horizontal federal learning; and sending the data of the terminal equipment group, wherein the data of the terminal equipment group comprises aggregation information of the measurement result of the QoS parameters.

In one possible design, the transceiver module 1120 is further configured to send a second request message to a user plane network element, where the second request message is used to request data of the terminal device group; and receiving the data of the terminal equipment group from the user plane network element.

In one possible design, the transceiver module 1120 is further configured to send a third request message to a user plane network element, where the third request message is used to request a measurement result of a QoS parameter of a terminal device in the terminal device group; receiving a measurement result of QoS parameters of terminal devices in the terminal device group from the user plane network element; the processing module 1110 is further configured to determine data of the terminal device group according to a measurement result of QoS parameters of terminal devices in the terminal device group and the first request message.

It should be understood that the apparatus 1100 according to the embodiment of the present application may correspond to the second network element in the foregoing method embodiment, and the operations and/or functions of each module in the apparatus 1100 are respectively for implementing the corresponding steps of the method of the second network element in the foregoing method embodiment, so that the beneficial effects in the foregoing method embodiment may also be implemented, which is not repeated herein for brevity.

When the apparatus 1100 is an application function network element or a chip in an application function network element, the processing module 1110 in the apparatus 1100 may support the apparatus 1100 to perform the actions of the application function network element in the method examples above. For example, processing module 1110 may support apparatus 1100 to perform steps 900 and 910 in fig. 9.

The transceiver module 1120 may support the apparatus 1100 in communication with a policy control network element, e.g., the transceiver module 1120 may support the apparatus 1100 to perform step 920 in fig. 9.

For example, the processing module 1110 is configured to obtain a transmission delay and a local computation delay of each terminal device in a terminal device group, where the terminal devices in the terminal device group are terminal devices participating in horizontal federal learning, and adjust QoS parameters of a first terminal device in the terminal device group according to the transmission delay and the local computation delay of each terminal device; the transceiver module 1120 is configured to send the adjusted QoS parameter of the first terminal device to a policy control network element.

In one possible design, when adjusting QoS parameters of a first terminal device in the terminal device group according to the transmission delay and the local computation delay of each terminal device, the processing module 1110 is configured to determine a statistic value of total delay of each terminal device according to the transmission delay and the local computation delay of each terminal device, where the total delay of each terminal device is a sum of the transmission delay and the local computation delay of the terminal device; and under the condition that the total time delay of the first terminal equipment is larger than a first preset threshold value or smaller than a second preset threshold value, adjusting the QoS parameters of the first terminal equipment, wherein the first preset threshold value and the second preset threshold value are determined according to the statistic value.

It should be understood that the apparatus 1100 according to the embodiment of the present application may correspond to the application function network element in the foregoing method embodiment, and the operations and/or functions of each module in the apparatus 1100 are respectively for implementing the corresponding steps of the method for applying the function network element in the foregoing method embodiment, so that the beneficial effects in the foregoing method embodiment may also be implemented, which is not repeated herein for brevity.

Fig. 12 shows a schematic structural diagram of a communication apparatus 1200 according to an embodiment of the present application. As shown in fig. 12, the apparatus 1200 includes: a processor 1201.

When the apparatus 1200 is a first network element or a chip in a first network element, in a possible implementation, the processor 1201 is configured to invoke the interface to perform the following actions: a first request message is sent to a second network element, wherein the first request message is used for requesting data of a terminal equipment group, and terminal equipment in the terminal equipment group is terminal equipment participating in transverse federal learning; receiving data of the terminal equipment group from the second network element, wherein the data of the terminal equipment group comprises aggregation information of measurement results of QoS parameters; according to the data of the terminal equipment group, qoS parameters of a first terminal equipment in the terminal equipment group are adjusted; and sending the adjusted QoS parameters of the first terminal equipment to a strategy control network element.

It should be understood that the apparatus 1200 may also be used to perform other steps and/or operations on the first network element side in the foregoing embodiments, which are not described herein for brevity.

When the apparatus 1200 is a second network element or a chip in a second network element, in a possible implementation, the processor 1201 is configured to invoke the interface to perform the following actions:

receiving a first request message from a first network element, wherein the first request message is used for requesting data of a terminal equipment group, and the terminal equipment in the terminal equipment group is terminal equipment participating in horizontal federal learning; and sending the data of the terminal equipment group, wherein the data of the terminal equipment group comprises aggregation information of the measurement result of the QoS parameters.

It should be understood that the apparatus 1200 may also be used to perform other steps and/or operations on the second network element side in the foregoing embodiments, which are not described herein for brevity.

When the apparatus 1200 is an application function network element or a chip in an application function network element, in a possible implementation, the processor 1201 is configured to invoke the interface to perform the following actions:

acquiring the transmission delay and the local computation delay of each terminal device in a terminal device group, wherein the terminal devices in the terminal device group are terminal devices participating in transverse federal learning, and adjusting the QoS parameters of a first terminal device in the terminal device group according to the transmission delay and the local computation delay of each terminal device; and sending the adjusted QoS parameters of the first terminal equipment to a strategy control network element.

It should be understood that the apparatus 1200 may also be used to perform other steps and/or operations on the network element side of the application function in the foregoing embodiments, which are not described herein for brevity.

It should be understood that the processor 1201 may invoke an interface to perform the above-mentioned transceiving actions, where the invoked interface may be a logical interface or a physical interface, which is not limited thereto. Alternatively, the physical interface may be implemented by a transceiver. Optionally, the apparatus 1200 further comprises a transceiver 1203.

Optionally, the apparatus 1200 further comprises a memory 1202, in which memory 1202 program codes in the above-described method embodiments may be stored for the processor 1201 call.

Specifically, if the apparatus 1200 includes a processor 1201, a memory 1202 and a transceiver 1203, the processor 1201, the memory 1202 and the transceiver 1203 communicate with each other through an internal connection path to transfer control and/or data signals. In one possible design, the processor 1201, the memory 1202, and the transceiver 1203 may be implemented by chips, and the processor 1201, the memory 1202, and the transceiver 1203 may be implemented in the same chip, or may be implemented in different chips, respectively, or any two of the functions may be combined in one chip. The memory 1202 may store program codes, and the processor 1201 invokes the program codes stored in the memory 1202 to implement the corresponding functions of the apparatus 1200.

The method disclosed in the embodiments of the present application may be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method embodiments may be implemented by integrated logic circuits of hardware in a processor or instructions in software form. The processor may be a general purpose processor, a digital signal processor (digital signal processor, DSP), an application specific integrated circuit (application specific integrated circuit, ASIC), an off-the-shelf programmable gate array (field programmable gate array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, a system on chip (SoC), a central processor (central processor unit, CPU), a network processor (network processor, NP), a digital signal processing circuit (digital signal processor, DSP), a microcontroller (micro controller unit, MCU), a programmable controller (programmable logic device, PLD) or other integrated chip. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present application may be embodied directly in hardware, in a decoded processor, or in a combination of hardware and software modules in a decoded processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method.

It will be appreciated that the memory in embodiments of the present application may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an electrically Erasable EPROM (EEPROM), or a flash memory. The volatile memory may be random access memory (random access memory, RAM) which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous DRAM (SLDRAM), and direct memory bus RAM (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to comprise, without being limited to, these and any other suitable types of memory.

It should be understood that, in the embodiments of the present application, the numbers "first" and "second" … are merely for distinguishing different objects, such as for distinguishing different parameter information or messages, and are not limited to the scope of the embodiments of the present application, but are not limited thereto.

It should also be understood that, in various embodiments of the present application, the size of the sequence numbers of the above-described processes does not mean that the execution sequence is sequential, and the execution sequence of each process should be determined by its functions and inherent logic. The various numbers or serial numbers referred to in the above processes are merely for convenience of description and should not be construed as limiting the implementation of the embodiments of the present application.

It should also be understood that the term "and/or" is merely one association relationship describing the associated object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.

Similar to the term "appearing in this application includes one or more of the following: the meaning of the expressions a, B, and C "generally means that the item may be any one of the following unless otherwise specified: a, A is as follows; b, a step of preparing a composite material; c, performing operation; a and B; a and C; b and C; a, B and C; a and A; a, A and A; a, A and B; a, a and C, a, B and B; a, C and C; b and B, B and C, C and C; c, C and C, and other combinations of a, B and C. The above is an optional entry for the item exemplified by 3 elements a, B and C, when expressed as "the item includes at least one of the following: a, B, … …, and X ", i.e. when there are more elements in the expression, then the entry to which the item is applicable can also be obtained according to the rules described above.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.

In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, or other various media capable of storing program codes.

Claims

1. A method of communication, the method comprising:

the method comprises the steps that a first network element sends a first request message to a second network element, wherein the first request message is used for requesting data of a terminal equipment group, and terminal equipment in the terminal equipment group is terminal equipment participating in transverse federal learning;

the first network element receives data of the terminal equipment group from the second network element, wherein the data of the terminal equipment group comprises aggregation information of measurement results of quality of service (QoS) parameters;

the first network element adjusts QoS parameters of first terminal equipment in the terminal equipment group according to the data of the terminal equipment group;

and the first network element sends the adjusted QoS parameters of the first terminal equipment to a strategy control network element.

2. The method of claim 1, wherein the first request message includes indication information for indicating a measurement result of the QoS parameter of the feedback terminal device;

3. The method of claim 2, wherein the first request message further comprises a feedback condition for indicating a condition to be satisfied for feeding back a measurement result of the QoS parameter of the terminal device;

And the measurement result of the QoS parameter of the second terminal equipment meets the feedback condition.

4. A method according to any of claims 1-3, characterized in that the aggregation information comprises an aggregate bit rate, which is used to characterize the sum of the bit rates of the QoS flows of the terminal devices in the group of terminal devices;

the first network element adjusts the QoS parameter of the first terminal equipment in the terminal equipment group according to the data of the terminal equipment group, and the method comprises the following steps:

and when the aggregate bit rate is greater than the subscription maximum bit rate of the terminal equipment group, the first network element adjusts the bit rate of the QoS stream of the first terminal equipment according to the data of the terminal equipment group.

5. The method according to any of claims 1-4, wherein the aggregated information comprises statistics of transmission delays of terminal devices in the group of terminal devices;

and if the statistical value of the transmission time delay is larger than a first preset threshold value, the first network element adjusts the bit rate of the QoS stream of the first terminal equipment according to the data of the terminal equipment group.

6. The method of claim 5, wherein the first terminal device is a terminal device having a transmission delay greater than a second predetermined threshold.

7. The method according to claim 6, wherein the first request message further comprises the first preset threshold and/or the second preset threshold.

8. The method according to any of claims 1-7, wherein the first request message comprises at least one of an identification of a terminal device in the group of terminal devices, an identification of the group of terminal devices, identification information of an analysis type, a type of the aggregation information.

9. The method of claim 8, wherein the first request message further comprises at least one of:

sending the triggering condition of the aggregation information;

and the application identifier is used for indicating the application corresponding to the measurement result of the QoS parameter of the terminal equipment.

10. The method according to any of claims 1-9, wherein the first network element is an application function network element and the second network element is a data analysis function network element or a policy control network element.

11. A method of communication, the method comprising:

the second network element receives a first request message from the first network element, wherein the first request message is used for requesting data of a terminal equipment group, and terminal equipment in the terminal equipment group is terminal equipment participating in transverse federal learning;

And the second network element sends the data of the terminal equipment group, wherein the data of the terminal equipment group comprises aggregation information of the measurement result of the QoS parameters.

12. The method of claim 11, wherein the first request message includes indication information for indicating a measurement result of the QoS parameter of the feedback terminal device;

13. The method of claim 12, wherein the first request message further comprises a feedback condition for indicating a condition to be satisfied for feeding back a measurement result of the QoS parameter of the terminal device;

14. The method according to any of claims 11-13, wherein the aggregation information comprises an aggregate bit rate, the aggregate bit rate being used to characterize a sum of bit rates of QoS flows of terminal devices in the group of terminal devices.

15. The method according to any of claims 11-14, wherein the aggregation information comprises statistics of transmission delays of terminal devices in the group of terminal devices.

16. The method according to any of claims 11-15, wherein the first request message comprises at least one of an identification of a terminal device in the group of terminal devices, an identification of the group of terminal devices, identification information of an analysis type, a type of the aggregation information.

17. The method of claim 16, wherein the first request message further comprises at least one of:

sending the triggering condition of the aggregation information;

18. The method of any one of claims 11-17, further comprising:

the second network element sends a second request message to the user plane network element, wherein the second request message is used for requesting the data of the terminal equipment group;

the second network element receives the data of the terminal equipment group from the user plane network element.

19. The method of any one of claims 11-17, further comprising:

the second network element sends a third request message to the user plane network element, wherein the third request message is used for requesting the measurement result of the QoS parameters of the terminal equipment in the terminal equipment group;

The second network element receives a measurement result of the QoS parameters of the terminal equipment in the terminal equipment group from the user plane network element;

the second network element determines data of the terminal equipment group according to the measurement result of the QoS parameters of the terminal equipment in the terminal equipment group and the first request message.

20. A method according to any of claims 11-19, wherein the first network element is an application function network element and the second network element is a data analysis function network element or a policy control network element.

21. A method of communication, the method comprising:

the method comprises the steps that an application function network element obtains transmission delay and local calculation delay of each terminal device in a terminal device group, wherein the terminal devices in the terminal device group are terminal devices participating in transverse federal learning;

the application function network element adjusts QoS parameters of a first terminal device in the terminal device group according to the transmission delay and the local calculation delay of each terminal device;

and the application function network element sends the adjusted QoS parameters of the first terminal equipment to a strategy control network element.

22. The method of claim 21, wherein the application function network element adjusts QoS parameters of a first terminal device in the group of terminal devices based on the transmission delays and the locally calculated delays of the respective terminal devices, comprising:

The application function network element determines the statistical value of the total time delay of each terminal device according to the transmission time delay and the local calculation time delay of each terminal device, wherein the total time delay of each terminal device is the sum of the transmission time delay and the local calculation time delay of the terminal device;

and when the total time delay of the first terminal equipment is larger than a first preset threshold or smaller than a second preset threshold, the application function network element adjusts the QoS parameters of the first terminal equipment, wherein the first preset threshold and the second preset threshold are determined according to the statistic value.

23. The method of claim 22, wherein the adjusted QoS parameters for the first terminal device comprise at least one of a resource type, a priority, a packet delay budget, a guaranteed stream bit rate, a maximum stream bit rate, an allocation and a preemption priority.

24. The method of any of claims 21-23, wherein the local computation delay is a length of time required to determine update parameters of the model of lateral federal learning;

the transmission delay is a time period required for transmitting the update parameter to the application function network element.

25. A communication device, comprising:

a memory for storing computer instructions;

a processor for executing the computer instructions to cause the communication device to perform the method of any of claims 1 to 10 and 11 to 20 and 21 to 24.

26. A communication device comprising a processor and interface circuitry for receiving signals from other communication devices than the communication device and transmitting signals from the processor to the processor or sending signals from the processor to other communication devices than the communication device, the processor being configured to implement the method of any of claims 1 to 10 and 11 to 20 and 21 to 24 by logic circuitry or executing code instructions.

27. A computer readable storage medium, characterized in that the storage medium has stored therein a computer program or instructions which, when executed by a communication device, implement the method of any of claims 1 to 10 and 11 to 20 and 21 to 24.

28. A communication system, the system comprising a first network element and a second network element;

The first network element for performing the method of any one of claims 1 to 10; and

the second network element being configured to perform the method of any of claims 11 to 20.