WO2023035895A1 - 一种数据处理方法、设备、可读存储介质和程序产品 - Google Patents

一种数据处理方法、设备、可读存储介质和程序产品 Download PDF

Info

Publication number
WO2023035895A1
WO2023035895A1 PCT/CN2022/113279 CN2022113279W WO2023035895A1 WO 2023035895 A1 WO2023035895 A1 WO 2023035895A1 CN 2022113279 W CN2022113279 W CN 2022113279W WO 2023035895 A1 WO2023035895 A1 WO 2023035895A1
Authority
WO
WIPO (PCT)
Prior art keywords
parameter
prediction
analysis
service
function
Prior art date
Application number
PCT/CN2022/113279
Other languages
English (en)
French (fr)
Inventor
张卓筠
Original Assignee
腾讯科技（深圳）有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 腾讯科技（深圳）有限公司 filed Critical 腾讯科技（深圳）有限公司
Priority to EP22866368.8A priority Critical patent/EP4231703A4/en
Publication of WO2023035895A1 publication Critical patent/WO2023035895A1/zh
Priority to US18/197,498 priority patent/US20230283529A1/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14—Network analysis or design
    • H04L41/147—Network analysis or design for predicting network behaviour
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W48/00—Access restriction; Network selection; Access point selection
    • H04W48/18—Selecting a network or a communication service
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W28/00—Network traffic management; Network resource management
    • H04W28/16—Central resource management; Negotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]
    • H04W28/24—Negotiating SLA [Service Level Agreement]; Negotiating QoS [Quality of Service]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W28/00—Network traffic management; Network resource management
    • H04W28/02—Traffic management, e.g. flow control or congestion control
    • H04W28/08—Load balancing or load distribution
    • H04W28/09—Management thereof
    • H04W28/0958—Management thereof based on metrics or performance parameters
    • H04W28/0967—Quality of Service [QoS] parameters
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W76/00—Connection management
    • H04W76/10—Connection setup
    • H04W76/11—Allocation or use of connection identifiers

Definitions

  • the present application relates to the technical field of communication, in particular to data processing.
  • QoS Quality of Service
  • QoS refers to the ability of a network to use various basic technologies to provide required services for specified network communications.
  • QoS is a network quality of service guarantee mechanism that can be used to guarantee network delay, bit error rate, data transmission rate, etc., according to QoS makes more reasonable use of network resources.
  • the 5G QoS model is based on QoS Flow (QoS Flow), which can support QoS flow with guaranteed bit rate (Guaranteed Bit Rate QoS Flow, GBR QoS Flow) and QoS flow without guaranteed bit rate (Non-GBR QoS Flow).
  • QoS Flow QoS Flow
  • PCC Policy Control and Charging
  • SMF When a protocol data unit session (Protocol Data Unit SeSSion, PDU SeSSion) is established, SMF will send the QoS rule to the terminal device (User Equipment, UE), and also send flow-level QoS parameters
  • the terminal device User Equipment, UE
  • QoS parameters For the UE, for example, for GBR QoS flows, it may include guaranteed flow bit rate (Guaranteed Flow Bit Rate, GFBR), maximum flow bit rate ( Maximum Flow Bit Rate, MFBR) or optional averaging window (Averaging Window) and other QoS parameters.
  • the UE After receiving the QoS rule and QoS parameters, the UE can apply the QoS rule to map the service data packets provided by the application program client on the UE to the corresponding QoS flow for the uplink service flow.
  • the 5G system also supports an alternative QoS configuration mechanism, that is, SMF can provide an alternative QoS profile (Alternative QoS Profile) to the radio access network (Radio Access Network, RAN), when the RAN side cannot meet the existing QoS parameters , will detect whether the QoS parameters defined in an alternative QoS configuration file (such as guaranteed flow bit rate, packet error rate, packet delay budget, etc.) The corresponding QoS parameters are further updated and sent to the UE.
  • SMF can provide an alternative QoS profile (Alternative QoS Profile) to the radio access network (Radio Access Network, RAN), when the RAN side cannot meet the existing QoS parameters , will detect whether the QoS parameters defined in an alternative QoS configuration file (such as guaranteed flow bit rate, packet error rate, packet delay budget, etc.)
  • QoS configuration file such as guaranteed flow bit rate, packet error rate, packet delay budget, etc.
  • the embodiments of the present application provide a data processing method, device, readable storage medium and program product, which can expand the ability of the application program client to perceive and predict service quality parameters in the service quality mechanism.
  • an embodiment of the present application provides a data processing method, the method is executed by a terminal device, the terminal device includes an application program client and an analysis and prediction function component, and the method includes:
  • the application client generates a parameter prediction request, and sends the parameter prediction request to the analysis and prediction function component;
  • the analysis and prediction function component predicts the predicted service quality parameters corresponding to the service quality flow for the application client, and sends the predicted service quality parameters to the application client; the service quality flow and the service provided by the application client packets are associated.
  • an embodiment of the present application provides a data processing method, the method is executed by a terminal device, the terminal device includes an application program client and an analysis and prediction function component, and the method includes:
  • the application client signs the parameter prediction notification function for the protocol data unit session with the analysis and prediction function component; the protocol data unit session is associated with the service data package provided by the application client;
  • the analysis and prediction function component predicts the predicted service quality parameters corresponding to the service quality flow for the application client based on the parameter prediction notification function; the service quality flow is associated with the business data packet;
  • the analysis and prediction function component sends the predicted quality of service parameter to the application client;
  • the QoS parameter is issued by the session management network element.
  • An embodiment of the present application provides a data processing method on the one hand, including:
  • the session management network element sends quality of service rules and quality of service parameter sets to the terminal equipment, so that the terminal equipment maps the service data packets sent by the application program client to the service quality flow based on the service quality rules; the terminal equipment includes application program customer
  • the terminal and the analysis and prediction function component the application client has the function of generating a parameter prediction request, and the parameter prediction request instructs the analysis and prediction function component to send the predicted service quality parameter corresponding to the service quality flow to the application client, and the predicted service quality parameter is determined by
  • the analysis and prediction function component predicts the service data packet based on the parameter prediction request; the quality of service parameter set includes the quality of service parameter associated with the quality of service flow.
  • An embodiment of the present application provides a data processing device on the one hand, the device runs in a terminal device, including:
  • the request sending module is used to send the parameter prediction request to the analysis and prediction function module; the parameter prediction request is generated by the application client corresponding to the protocol data unit session; the application client runs in the terminal device;
  • the analysis and prediction function module is used to predict the predicted service quality parameters corresponding to the service quality flow for the application client based on the parameter prediction request, and send the predicted service quality parameters to the application client; the service quality flow and the application client provide associated with the business data package.
  • An embodiment of the present application provides a data processing device on the one hand, the device runs in a terminal device, including:
  • the signing module is used to sign the parameter prediction notification function associated with the application client with the analysis and prediction function module;
  • the application client is the client corresponding to the protocol data unit session, and the application client runs in the terminal device;
  • An analysis and prediction function module used for predicting service quality parameters corresponding to the service quality flow for the application program client based on the parameter prediction notification function; the service quality flow is associated with the business data package provided by the application program client;
  • the above analysis and prediction function module is also used to send the predicted quality of service parameter to the application client when the predicted quality of service parameter is different from the quality of service parameter associated with the quality of service flow or when the predicted quality of service parameter exceeds the threshold value;
  • the QoS parameters associated with the quality flow are issued by the session management network element.
  • an embodiment of the present application provides a network element device, the device runs in a session management network element, including:
  • the sending module is configured to send quality of service rules and quality of service parameter sets to the terminal device, so that the terminal device maps the service data packets sent by the application client corresponding to the protocol data unit session to the quality of service based on the quality of service rules Flow;
  • the terminal device includes an application client and an analysis and prediction function component.
  • the application client has the function of generating a parameter prediction request, and the parameter prediction request instructs the analysis and prediction function component to send the predicted service quality parameters corresponding to the service quality flow to the application client
  • the predicted QoS parameter is obtained by the analysis and prediction function component based on the parameter prediction request predicted for the service data packet;
  • the QoS parameter set includes QoS parameters associated with the QoS flow.
  • An embodiment of the present application provides a computer device, including: a processor, a memory, and a network interface;
  • the above-mentioned processor is connected to the above-mentioned memory and the above-mentioned network interface, wherein the above-mentioned network interface is used to provide data communication functions, the above-mentioned memory is used to store computer programs, and the above-mentioned processor is used to call the above-mentioned computer programs, so that the computer equipment executes the implementation of the present application. method in the example.
  • An embodiment of the present application provides a network element device, including: a processor, a memory, and a network interface;
  • the above-mentioned processor is connected to the above-mentioned memory and the above-mentioned network interface, wherein the above-mentioned network interface is used to provide a data communication function, the above-mentioned memory is used to store a computer program, and the above-mentioned processor is used to call the above-mentioned computer program, so that the network element device executes the application Methods in the Examples.
  • An embodiment of the present application provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and the computer program is adapted to be loaded by a processor and execute the method in the embodiment of the present application.
  • Embodiments of the present application provide a computer program product or computer program on the one hand, the computer program product or computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium, and the processor of the computer device or network element device The computer-readable storage medium reads the computer instruction, and the processor executes the computer instruction, so that the computer device or the network element device executes the method in the embodiment of the present application.
  • the embodiment of the present application can support the application program client on the terminal device to generate a parameter prediction request, and send the parameter prediction request to the analysis and prediction function component in the terminal device, and then the analysis and prediction function component can be based on the parameter prediction request and generate a parameter prediction request for the application program.
  • the client predicts the predicted QoS parameter corresponding to the QoS flow, and finally can send the predicted QoS parameter to the application program client.
  • the analysis and prediction function component can respond to the parameter prediction request sent by the application program client running on the terminal device, and predict the corresponding service quality parameters for the application program client, so that the subsequent application program client can be based on
  • the predicted service quality parameters are adaptively adjusted, so that the ability of the application client to perceive and predict the service quality parameters can be expanded in the service quality mechanism.
  • FIG. 1 is a schematic diagram of a system architecture provided by an embodiment of the present application.
  • FIG. 2 is a schematic diagram of a data processing scenario provided by an embodiment of the present application.
  • Fig. 3 is a schematic flow chart of a data processing method provided by an embodiment of the present application.
  • FIG. 4 is an interactive schematic diagram of a data processing process provided by an embodiment of the present application.
  • FIG. 5 is a schematic flow diagram of a data processing method provided in an embodiment of the present application.
  • FIG. 6 is an interactive schematic diagram of a parameter prediction notification process provided by an embodiment of the present application.
  • FIG. 7 is a schematic flow chart of a data processing method provided by an embodiment of the present application.
  • FIG. 8 is a schematic flowchart of a data processing method provided in an embodiment of the present application.
  • FIG. 9 is a schematic flowchart of a data processing method provided in an embodiment of the present application.
  • FIG. 10 is a schematic structural diagram of a data processing device provided in an embodiment of the present application.
  • Fig. 11 is a schematic structural diagram of a data processing device provided by an embodiment of the present application.
  • FIG. 12 is a schematic structural diagram of a network element device provided in an embodiment of the present application.
  • Fig. 13 is a schematic structural diagram of a computer device provided by an embodiment of the present application.
  • FIG. 14 is a schematic structural diagram of a network element device provided in an embodiment of the present application.
  • FIG. 15 is a schematic structural diagram of a data processing system provided by an embodiment of the present application.
  • the technical solution of the embodiment of the present application can be applied to various communication systems, such as: Global System for Mobile Communication (Global System for Mobile communication, GSM), Code Division Multiple Access (Code Division Multiple Access, CDMA) system, wideband code division multiple access (Wideband Code Division Multiple Access, WCDMA) system, General Packet Radio Service (GPRS), Long Term Evolution (LTE) system, LTE Frequency Division Duplex (FDD) system, LTE Time Division Duplex (TDD), Universal Mobile Telecommunications System (UMTS), Worldwide Interoperability for Microwave Access (WiMAX) communication system, the future fifth generation (5th Generation, 5G) mobile communication system or subsequent evolved mobile communication system, etc.
  • GSM Global System for Mobile Communication
  • CDMA Code Division Multiple Access
  • WCDMA Wideband Code Division Multiple Access
  • GPRS General Packet Radio Service
  • LTE Long Term Evolution
  • FDD Frequency Division Duplex
  • TDD Time Division Duplex
  • UMTS Universal Mobile Telecommunications System
  • WiMAX Worldwide Interoperability for
  • FIG. 1 is a schematic diagram of a system architecture provided by an embodiment of the present application.
  • the system architecture can be applied to business scenarios supporting uplink services (such as streaming media services), such as video conferencing, video-on-demand, distance education and other multimedia real-time services.
  • uplink services such as streaming media services
  • QoS Quality of Service
  • the applications corresponding to these different services require different QoS (Quality of Service) requirements have led to a rapid increase in the demand for quality of service in various applications.
  • QoS Quality of Service
  • QoS is an agreement on the quality of information transmission and sharing between the network and users and between users communicating with each other on the network. For example, transmission delay time, guaranteed bit rate of data transmission, etc., are used to solve network delays and congestion. A technique for such problems.
  • QoS is very necessary for some key applications and multimedia applications.
  • QoS can ensure that important business streams (such as audio and video streams generated during live broadcast) are not delayed or discarded, while ensuring network efficiency. run.
  • the system architecture may include a service server 100 and a terminal cluster
  • the terminal cluster may include: terminal equipment 200a, terminal equipment 200b, terminal equipment 200c, ..., terminal equipment 200n, wherein there may be communication between the terminal clusters Connection, for example, there is a communication connection between the terminal device 200a and the terminal device 200b, and there is a communication connection between the terminal device 200a and the terminal device 200c.
  • any terminal device in the terminal cluster can have a communication connection with the service server 100, for example, there is a communication connection between the terminal device 200a and the service server 100, wherein the above-mentioned communication connection does not limit the connection mode, for example, it can be connected through a 4G wireless connection. Access methods, or 5G wireless access methods, etc., which are not limited in this application.
  • each terminal device in the terminal cluster as shown in Figure 1 can be installed with an application program client, and when the application program client runs in each terminal device, it can be connected with the business services shown in Figure 1 above.
  • Data interaction is performed between the servers 100, so that the service server 100 can receive service data from each terminal device.
  • the application client can be a live broadcast application, a social application, an instant messaging application, a game application, a short video application, a video application, a music application, a shopping application, a novel application, a payment application, a browser, etc.
  • Application client for data information functions such as audio and video.
  • the application client can be an independent client, or an embedded sub-client integrated in a certain client (such as instant messaging client, social client, video client, etc.), which will not be described here. limited.
  • the service server 100 may be a collection of multiple servers including a background server and a data processing server corresponding to the live broadcast application. Therefore, each terminal device can communicate with the service server through the application client corresponding to the live broadcast application 100 to perform data transmission, such as the anchor user can perform live broadcast through the application client corresponding to the live broadcast application installed on the terminal device (for example, terminal device 200a) held by him, other terminal devices (for example, terminal device 200b, terminal device 200a) 200c and terminal equipment 200n, etc.) can participate in the live broadcast through the service server 100.
  • live broadcast refers to the collection of data of the host party through audio and video collection equipment, and after a series of processing, such as compressing video coding into a video stream that can be watched and transmitted (or compressed into an audio stream that can be listened to and transmitted through audio coding), Technology that outputs to the viewing client.
  • the system architecture shown in Figure 1 may also include a radio access network (Radio Access Network, RAN), a bearer network (that is, a transmission network) and a core network, and the access network may deploy Multiple access network elements (also called access network equipment, such as 5G base station gNB), are mainly responsible for the access and management of terminal equipment on the wireless side;
  • the bearer network can be composed of a series of switching and routing equipment of operators , mainly used to transmit control signaling and user data between the wireless access network and the core network;
  • the core network can deploy a series of core network elements (also called core network equipment, "network elements” can also be called “Network functions”), these core network elements cooperate to perform authentication, charging and mobility management on terminal equipment, etc.
  • the core network elements may include Mobility Management Entity (MME), broadcast multi Broadcast Multicast Service Center (Broadcast Multicast Service Center, BMSC), etc., or may also include corresponding functional entities in the 5G system, such as session management network elements, mobility management network elements, policy control network elements, etc.
  • MME Mobility Management Entity
  • Broadcast Multicast Service Center Broadcast Multicast Service Center
  • the network element of the core network and the network element of the access network may be independent and different physical devices, or the functions of the network elements of the core network and the functions of the network elements of the access network may be integrated on the same physical device, or they may be A physical device integrates some functions of core network elements and some functions of access network elements. Terminal equipment can be fixed or mobile.
  • SMF Session Management Function, session management function: mainly responsible for session establishment, modification and release, user plane selection and control, UE IP (UE, User Equipment, that is, terminal equipment or user equipment; IP, Internet Protocol, that is Internet Protocol) address allocation, etc.
  • UE IP UE, User Equipment, that is, terminal equipment or user equipment
  • IP Internet Protocol, that is Internet Protocol
  • the SMF may also be called a session management network element.
  • UPF User Plane Function, user plane function: mainly responsible for data routing and forwarding of the user plane of the mobile core network, and interconnection with external data networks (Data Network, such as operator services, Internet or third-party services, etc.) .
  • Data Network such as operator services, Internet or third-party services, etc.
  • UPF is the main module for processing user plane data in the 5G core network.
  • the UPF may also be called a user plane network element.
  • PCF Policy Control Function, Policy Control Function
  • UDR Unified Data Repository, Unified Data Repository
  • PCF Policy Control Function
  • the network element of the access network is the access device for the terminal equipment to access the mobile communication system through wireless means, which can be a base station NodeB, an evolved base station eNodeB, a base station (gNodeB, gNB) in a 5G mobile communication system, a
  • the base station in the mobile communication system or the access node in the wireless fidelity (Wireless Fidelity, WiFi) system, etc. can also be a wireless controller in a cloud radio access network (Cloud Radio Access Network, CRAN) scenario, or can be a Relay stations, access points, vehicle-mounted devices, wearable devices, and network devices in the future 5G network or network devices in the future evolved PLMN network (Public Land Mobile Network, public land mobile communication network), etc., the embodiments of this application are docked
  • the specific technology and specific equipment form adopted by the network elements entering the network are not limited.
  • Terminal equipment can refer to user equipment (User Equipment, UE), access terminal, terminal in V2X (Vehicle to X) communication, user unit, user station, mobile station, mobile station, remote station, remote terminal, Mobile device, user terminal, wireless communication device, user agent or user device.
  • UE User Equipment
  • V2X Vehicle to X
  • the terminal equipment can also be a cellular phone, a cordless phone, a Session Initiation Protocol (Session Initiation Protocol, SIP) phone, a wireless local loop (Wireless Local Loop, WLL) station, a personal digital processing (Personal Digital Assistant, PDA), a wireless communication Functional handheld devices, computing devices or other processing devices connected to wireless modems, vehicle-mounted devices, wearable devices, terminal devices in the future 5G network or terminal devices in the future evolved public land mobile communication network (PLMN), etc., this The embodiment of the application does not limit this.
  • the terminal device may also include a V2X device, such as a vehicle or an On Board Unit (OBU) in the vehicle.
  • V2X device such as a vehicle or an On Board Unit (OBU) in the vehicle.
  • the aforementioned session management network element, user plane network element, policy control network element, and access network element are just a name, and the name does not constitute a limitation on the device itself.
  • the session management network element may also be called a session management function entity, or a session management function, etc., and this application does not limit the name of the device.
  • the network elements mentioned in the embodiments of the present application may also have other names, which are not limited.
  • the session management network element, the user plane network element, and the policy control network element may be separate network elements, or may be jointly implemented by multiple network elements, or may be used as functional modules within one network element.
  • This application The embodiment does not limit this.
  • system architecture shown in FIG. 1 can be applied to a 5G network and other possible networks in the future, which is not specifically limited in this embodiment of the present application.
  • the terminal device 200a and the terminal device 200b are taken as examples for description.
  • the terminal device 200a can collect the original audio and video data of the anchor user in real time, and pre-process the original audio and video data (such as image beautification, stylization) , and then the pre-processed audio and video data can be encoded (that is, digitized) and processed (such as audio and video mixing, packaging, etc.), so as to obtain a usable audio and video stream (that is, the general name of audio and video streams).
  • encoding reduces the amount of data by compressing audio and video data, which can facilitate the push, pull and storage of audio and video data, thereby greatly improving storage and transmission efficiency.
  • Commonly used encoding methods include CBR (Constant Bit Rate, constant bit rate, a fixed sampling rate compression method), VBR (Variable Bit Rate, variable bit rate), for video data
  • commonly used encoding standards include H.265 ( H.265-HEVC (High Efficiency Video Coding), a high-efficiency video coding standard passed by the ITU in 2013), H.264 (a highly compressed digital video codec standard jointly proposed by the ITU and the International Organization for Standardization) , MPEG-4 (Moving Picture Experts Group 4, a solution suitable for low transmission rate applications launched by the Moving Picture Experts Group in 1999), etc., which can be packaged as MKV (Matroska Video File), AVI (Audio Video Interleaved), MP4 (an abbreviation of MPEG-4) and other file formats; for audio data, commonly used encoding standards include
  • the terminal device 200a can send the encoded audio and video stream to the service server 100.
  • the service server 100 is deployed in a data network (Data Network, DN) outside the mobile communication network, such as the Internet ( Internet), WAP (Wireless Application Protocol, wireless application protocol), enterprise intranet, etc.
  • the terminal device 200a can send the audio and video stream to the base station, and then the base station forwards the audio and video stream to the 5G core network (5G Core, which can
  • the core network element UPF that is, the user plane network element) in the 5GC for short
  • the service server 100 in the external data network after being forwarded by the core network element UPF
  • Other core network elements in the network are mainly network elements of the control plane, responsible for processing signaling, implementing mobility management, session management, policy control, etc., thereby controlling the entire process.
  • the service server 100 can send the audio and video stream to other terminal devices in the virtual live broadcast room through the core network element UPF and the base station, for example, to the terminal device 200b, and the terminal device 200b can pass relevant hardware or The software decodes the received audio and video streams to obtain images or sounds that can be directly displayed, and then play the corresponding images or sounds.
  • RTMP Real Time Messaging Protocol, real-time messaging protocol
  • RTSP Real Time Streaming Protocol, real-time streaming protocol
  • Transmission protocols such as RTP (Real-time Transport Protocol, Real-time Transport Protocol) or RTCP (Real-time Transport Control Protocol, Real-time Transport Control Protocol) transmit audio and video streams.
  • the business server in the embodiment of the present application can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, and can also provide cloud database, cloud service, cloud computing, cloud Cloud servers for basic cloud computing services such as functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.
  • Terminal devices can be smartphones, tablet computers, laptops, desktop computers, handheld computers, mobile internet devices (mobile internet devices, MIDs), wearable devices (such as smart watches, smart bracelets, etc.), smart computers, smart vehicle devices etc. can run the above-mentioned application program client (such as the application program client terminal of the live application).
  • the QoS capability may be configured for the system architecture described above in FIG. 1 .
  • a QoS flow is the finest granularity of QoS distinction in a PDU session (that is, a protocol data unit session).
  • the same traffic forwarding processing (such as scheduling, admission threshold, etc.) will be used for the same QoS flow control service flow.
  • one or more PDU sessions can be established with the 5G network; one or more QoS flows can be established in each PDU session.
  • Each QoS flow is identified by a QoS flow identifier (QFI), and a QFI uniquely identifies a QoS flow in a PDU session.
  • QFI QoS flow identifier
  • each QoS flow corresponds to a data radio bearer (Data Radio Bearer, DRB), and a DRB can correspond to one or more QoS flows.
  • DRB Data Radio Bearer
  • whether a QoS flow is a GBR QoS flow or a Non-GBR QoS flow is determined by the corresponding QoS profile (QoS Profile).
  • the 5G core network supports the PDU connection service between the terminal device and the data network.
  • the PDU connection service is embodied in the form of a PDU session.
  • a PDU session refers to a data path for communication between a terminal device and the data network.
  • the terminal device can initiate a PDU session establishment to the core network element SMF (that is, the session management network element) in the 5G core network Request, during the PDU session establishment process, the core network element SMF can bind the PCC rules (i.e.
  • the core network element SMF can provide the new QoS flow Allocate QFI, and derive its QoS configuration file, corresponding UPF instructions, and QoS rules from the PCC rules bound to the QoS flow and other information provided by the core network element PCF (ie, the policy control element), and then, the core network
  • the network element SMF can send the QoS configuration file to the radio access network (R)AN (that is, the access network element), send the corresponding UPF command to the core network element UPF, and send the QoS rule to the terminal device.
  • R radio access network
  • the core network element SMF can also send flow level QoS parameters (QoS Flow level QoS parameter) to the terminal device at the same time, and these QoS parameters are associated with the corresponding QoS rules.
  • QoS Flow level QoS parameter QoS Flow level QoS parameter
  • the terminal device can classify and mark the uplink service flow (also called uplink user plane flow) based on the QoS rule. For example, the service flow (such as audio Video streams) are mapped to QoS streams, and then the QoS streams can be bound to AN resources (AN resources, such as data radio bearer DRB in the 3GPP radio access network scenario).
  • AN resources such as data radio bearer DRB in the 3GPP radio access network scenario.
  • one QoS flow can be associated with one or more QoS rules.
  • the embodiment of the present application can also provide an alternative QoS configuration file.
  • the core network network The Meta-SMF shall also provide the Radio Access Network (R)AN with a prioritized list of alternative QoS profiles. If the core network element SMF provides the radio access network (R)AN with a new priority list of alternative QoS profiles (if the corresponding PCC rule information changes), the radio access network (R)AN will use It replaces any previously stored list.
  • the replacement QoS configuration file can represent the combination of QoS parameters that the service flow can adapt to, and the combination of QoS parameters can include guaranteed flow bit rate (Guaranteed Flow Bit Rate, GFBR), packet error rate (Packet Error Rate, PER) and packet Delay budget (Packet Delay Budget, PDB).
  • QoS parameters can include guaranteed flow bit rate (Guaranteed Flow Bit Rate, GFBR), packet error rate (Packet Error Rate, PER) and packet Delay budget (Packet Delay Budget, PDB).
  • the radio access network (R)AN when the radio access network (R)AN sends a notification that the QoS profile is not satisfied to the core network element SMF, if the currently satisfied parameter value matches the alternative QoS profile, the radio access network (R)AN also A reference to an alternative QoS configuration file should be included to indicate the current QoS satisfied by the radio access network (R)AN, and then relevant notifications can be sent to the core network element SMF, and the core network element SMF will further update the corresponding QoS parameters and sent to the terminal device.
  • QoS parameters will affect the radio access network (R)AN's scheduling algorithms and strategies for different levels of users and services.
  • the base station can guide the resource allocation of the wireless side based on the above-mentioned QoS parameters and other core network parameters.
  • the embodiment of the present application provides a service transmission optimization method.
  • the application client such as a live application
  • the application client can generate a parameter prediction request, and then the parameter can be predicted
  • the request is sent to the analysis and prediction function component, wherein the application program client runs in the terminal device, and the analysis and prediction function component is also integrated in the terminal device.
  • the analysis and prediction function component can predict the predicted service quality parameter corresponding to the QoS flow associated with the service data packet for the application program client based on the parameter prediction request, and then can send the predicted service quality parameter to the application program client.
  • the analysis and prediction function component on the terminal device can predict the parameter change of a certain QoS flow according to the past QoS parameter information (that is, the historical parameter information).
  • GFBR value if the pattern repeats in history, then the analysis and prediction function component can predict that the QoS of the service quality flow X1 may reduce the GFBR at the location X2, so the analysis and prediction function component can use the predicted GFBR (that is, the predicted service quality parameter) to the application client X3 corresponding to the QoS flow X1.
  • the application client on the terminal device can perceive the predicted QoS parameter and its changes, so it can use the predicted QoS parameter to perform some related processing work, for example, it can perform adaptive adjustment based on the predicted QoS parameter, Therefore, the ability of the application program client to obtain and use the predicted service quality parameters can be expanded in the QoS mechanism.
  • the method provided by the embodiment of this application is very effective for upstream streaming media services.
  • the application client can adjust the encoding algorithm based on the predicted service quality parameters, thereby improving the transmission efficiency. , Concert live broadcast, UAV image return, road camera video return, etc.
  • FIG. 2 is a schematic diagram of a data processing scenario provided by an embodiment of the present application.
  • the implementation process of the data processing scenario is mainly carried out inside the terminal device (ie UE).
  • the terminal device A in this embodiment of the present application may be any terminal device, for example, it may be the terminal device 200a shown in FIG. 1 above.
  • one or more application program clients can be installed and run on the terminal device A, assuming that there are N application program clients in total, where N is a positive integer, respectively application program client A1, application program Client A2, ..., application program client AN, each application program client can correspond to one or more types of business, when the user has a certain business requirement, he can choose to run a certain application program on the terminal device A
  • the client obtains the corresponding application service.
  • the application client can perform data transmission with the corresponding server.
  • the application client may transmit some uplink information to the server, such as camera, microphone, etc.
  • the audio and video streams collected and processed by the device that is, the upstream service streams, in order to improve the service quality of network services, the embodiment of the present application can provide different forwarding processing for these service streams based on the QoS stream.
  • the session management network element can determine the establishment of a quality of service flow according to the local policy or the PCC rule sent by the policy control network element, and then the session management network element can access and move Access and Mobility Management Function (AMF for short, also called access and mobility management function) and radio access network (RAN, access network element) send quality of service rules and A QoS parameter set composed of QoS parameters corresponding to the flow level, where a QoS rule can include the QFI of the related QoS flow, a Packet Filter Set (Packet Filter Set) and a priority value, which need to be explained Yes, a packet filter set can contain multiple packet filters, and each packet filter can be upstream or downstream or bidirectional.
  • AMF Access and Mobility Management Function
  • RAN access network element
  • terminal device A can obtain multiple QoS rules such as QoS rule R1, QoS rule R2, and QoS rule R3, as well as QoS parameters related to these QoS rules. Parameter set; the session management network element can send the QoS configuration file related to the quality of service flow to the wireless access network through the access and mobility management network element; send the service data flow (Service Data Flow, SDF) information, the SDF information includes QoS control information.
  • SDF Service Data Flow
  • QoS flows can be established among terminal equipment A, radio access network and user plane network elements, for example, QoS flow F1, QoS flow F2, QoS flow F3, etc.
  • the radio access network can be configured according to QoS
  • the file establishes the data radio bearer of the air interface (that is, DRB, which belongs to AN resources), and stores the binding relationship between the quality of service flow and the data radio bearer.
  • DRB which belongs to AN resources
  • the quality of service flow F1 and the quality of service flow F2 are bound to the data radio bearer D1
  • the service The quality flow F3 is bound to the data radio bearer D2.
  • the embodiment of the present application does not specifically limit the quantity of QoS flows, QoS rules, and data radio bearers.
  • the terminal device A determines to send an uplink service data packet (UL packet), as shown in Figure 2, it is assumed that a service flow C is generated in the PDU session, which includes possible Service data packets of any one or more application clients on terminal device A, for example, application client A1, then for a PDU session of IP type (Type IP) or Ethernet type (Type Ethernet), terminal device A
  • the upstream packet filter (UL Packet Filter) in the packet filter set in the quality of service rule can be evaluated according to a certain priority order to the service data packet in the service flow C until a matching QoS rule; if no matching QoS rule is found, terminal device A will discard the service data packet.
  • the default quality of service rule does not include a packet filter set, and all uplink business data packets will be allowed. It should be noted that, for unstructured PDU sessions, only default QoS rules exist. Furthermore, terminal device A can use the QoS flow identifier (QFI) in the matched quality of service rule to map the service data packet in service flow C to the corresponding service quality flow, that is, use the QoS flow identifier to mark the service data packet .
  • QFI QoS flow identifier
  • some service data packets in service flow C can be mapped to service quality flow F1 according to service quality rule R1
  • some service data packets in service flow C can be mapped to service quality flow F1 according to service quality rule R2
  • service quality rule R3 For the quality flow F2, another part of service data packets in the service flow C can be mapped to the quality of service flow F3 according to the quality of service rule R3.
  • the above service data packets can be transmitted on the corresponding data radio bearers, for example, the service data packets in the QoS flow F1 and the service data packets in the QoS flow F2 Service data packets can be transmitted on the data radio bearer D1, and service data packets in the quality of service flow F3 can be transmitted on the data radio bearer D2.
  • the radio access network receives the service data packets transmitted over the data radio bearer D1 and radio bearer D2, it can transmit the service data packets to the user plane network elements through the N3 interface.
  • the user plane network elements After receiving the service data packets, the user plane network elements can Based on the QoS flow identification, it is verified whether these service data packets are transmitted with the correct quality of service flow, and the service data packets are processed accordingly according to the service detection, forwarding, reporting and charging rules issued by the session management network element.
  • the embodiment of the present application does not expand the processing flow of the downlink (that is, DL).
  • analysis and prediction function component B is also integrated on the terminal device A, and the analysis and prediction function component B can predict the corresponding service quality parameters for the application program client on the terminal device A, in an optional In an implementation manner, the analysis and prediction function component B may provide an analysis and prediction interface for the application client to call.
  • the application client corresponding to the PDU session on terminal device A can generate and send a parameter prediction request to the analysis and prediction function component B, and the analysis and prediction function component B receives the parameter prediction request Afterwards, the parameter prediction request can be responded to, that is, based on the parameter prediction request, the application program client can predict the predicted service quality parameter corresponding to the target quality of service flow associated with its service data packet, and then the predicted service quality parameter can be returned to to the application client.
  • the application client A1 can initiate a parameter prediction request through the analysis and prediction interface, and then analyze and predict the functional components B can determine that the service data packet of the application program client A1 belongs to the service quality flow F1, and then can send the service quality parameter E (that is, the predicted service quality parameter) predicted for the service quality flow F1 to the application program through the analysis and prediction interface Client A1.
  • the service quality parameter E that is, the predicted service quality parameter
  • the analysis and prediction function component B when the analysis and prediction function component B predicts that the actual QoS parameter of the QoS flow F1 may change (that is, has a changing trend), it can notify the application client A1, for example, according to the prediction Generate a parameter change notification message based on the received change trend, and send the parameter change notification message to the application client A1, and then the application client A1 can re-initiate the parameter prediction request, or, the analysis and prediction function component B can send the analysis and prediction results to (that is, the predicted quality of service parameter) is added to the parameter change notification message and then sent to the application program client A1.
  • the analysis and prediction interface provided by the above analysis and prediction function component B is an interface inside the terminal device A, and the process of predicting the corresponding service quality parameters is realized inside the terminal device A.
  • the application client can use the predicted service quality parameter.
  • the application client A1 is a client related to streaming media services (such as live broadcast services)
  • the application client A1 can make adaptive adjustments, for example, it can adjust the encoding algorithm it adopts based on the quality of service parameter E (such as adjusting the encoding rate, compression rate, etc., which needs to be considered comprehensively), so that After obtaining the optimized service data packet, terminal device A can still send the uplink optimized service data packet through the foregoing process, so that the purpose of saving transmission bandwidth and improving transmission efficiency can be achieved.
  • the application client can also use the predicted service quality parameters to perform other processing, such as adjusting other transmission parameters of its streaming media service. How to use it is an internal implementation of the application client, which is not limited in this application.
  • FIG. 3 is a schematic flowchart of a data processing method provided by an embodiment of the present application.
  • the data processing method can be executed by a terminal device.
  • the method provided by the embodiment of the present application can support the analysis and prediction function component in the terminal device to predict the parameter change of the corresponding QoS flow for the application client on the terminal device according to the historical parameter information of the quality of service parameter (ie QoS parameter).
  • the data processing method may at least include the following S101-S102:
  • the application client generates a parameter prediction request, and sends the parameter prediction request to the analysis and prediction function component;
  • the application client when the terminal device establishes a protocol data unit session (that is, a PDU session) or after the protocol data unit session is established, the protocol data
  • the application client corresponding to the unit session can generate and send a parameter prediction request to the analysis and prediction function component (also called an analysis and prediction function module) on the terminal device, and then the analysis and prediction function component can receive the parameter prediction request.
  • the parameter prediction request is used to request for the application program client to predict the QoS flow corresponding to the service flow (ie QoS flow) or the QoS parameter of the QoS flow in the corresponding network slice (ie the predicted QoS parameter) .
  • the application client runs on the terminal device, and may be a client supporting uplink services (for example, transmitting text, image, audio or video data to the server).
  • the analysis and prediction function component on the terminal device can provide an API interface (Application Programming Interface, that is, an application program interface) for the application program client to call.
  • the API interface can be called analysis Prediction interface, or also called the analysis and prediction function interface, this application does not limit the specific name of the interface
  • the application client can use the prediction-related service quality parameters provided by the analysis and prediction function component by calling the analysis and prediction interface That is to say, the application client can send a parameter prediction request to the analysis and prediction interface, and then the analysis and prediction function component can obtain the parameter prediction request through the analysis and prediction interface.
  • the analysis and prediction function component predicts the predicted service quality parameters corresponding to the service quality flow for the application program client, and sends the predicted service quality parameters to the application program client; the service quality flow and the application program client provide associated with the business data package.
  • the analysis and prediction function component of the terminal device may predict the QoS parameter corresponding to the QoS flow for the application program client according to the parameter prediction request.
  • the predicted service quality parameter is generated by the analysis and prediction function component.
  • the predicted QoS parameters that can be provided by the terminal device include one or more of the following QoS parameters: Guaranteed Stream Bit Rate (GFBR), Packet Error Rate (PER), and Packet Delay Budget (PDB).
  • GFBR Guaranteed Stream Bit Rate
  • PER Packet Error Rate
  • PDB Packet Delay Budget
  • the guaranteed flow bit rate means the minimum bit rate guaranteed by the network to provide the quality of service flow in the average time window;
  • the packet error rate means the upper limit of the non-congestion-related data packet loss rate;
  • the session management network element can issue QoS rules and service A quality parameter set, wherein the quality of service rules can be used to classify and mark uplink service flows, and the quality of service parameters in the quality of service parameter set are associated with the quality of service rules.
  • the terminal device may map the service data packet sent by the application program client to the corresponding QoS flow based on the received QoS rule, wherein the target QoS parameter associated with the QoS flow belongs to the QoS parameter set. It can be understood that since the business data packets mapped to the same QoS flow will be marked with the same QoS flow ID, the analysis and prediction function component can determine which QoS flow the business data packet of the application client belongs to through the QoS flow ID.
  • the quality of service parameter set may also include but not limited to the following QoS parameters: 5G QoS identifier (5G QoS identifier, 5QI ), Allocation and Retention Priority (ARP), Maximum Flow Bit Rate (MFBR), Reflective QoS Attribute (Reflective QoS Attribute, RQA), Quality of Service Notification Control (QoS Notification Control, QNC), priority level (Priority Level).
  • QoS parameters 5G QoS identifier, 5QI ), Allocation and Retention Priority (ARP), Maximum Flow Bit Rate (MFBR), Reflective QoS Attribute (Reflective QoS Attribute, RQA), Quality of Service Notification Control (QoS Notification Control, QNC), priority level (Priority Level).
  • the analyzing and predicting function component may analyze and predict the change of the QoS parameter of the QoS flow corresponding to the service flow on the terminal device. Specifically, after the analysis and prediction function component on the terminal device receives the parameter prediction request through the analysis and prediction interface, it can obtain the service quality flow identifier (that is, QFI) associated with the application client according to the parameter prediction request, and identify the The quality of service flow corresponding to the quality of service flow identifier. Further, the analysis and prediction function component can predict the predicted quality of service parameter corresponding to the quality of service flow based on the historical parameter information corresponding to the target quality of service parameter.
  • the service quality flow identifier that is, QFI
  • the target service quality can be The historical parameter information corresponding to the quality parameter is input into the pre-trained parameter prediction model, through which the parameter change feature corresponding to the historical parameter information can be extracted, and then the target service quality parameter can be adjusted based on the parameter change feature, thus obtaining The predicted QoS parameter corresponding to the QoS flow.
  • the historical parameter information may include the change of the QoS parameter of the QoS flow corresponding to the service flow on the application program client within a statistical time period
  • the parameter change feature may represent an influencing factor that may cause the change, such as an environmental factor (time , location, etc.), connected data network or network slice, etc.
  • the prediction function component can extract the corresponding parameter change feature W1 (related to the target time period) through the parameter prediction model, and then can predict the GFBR value that may reduce the QoS flow in the target time period based on the parameter change feature W1, then it can The current GFBR value of the QoS flow is adjusted to a lower value, and then the adjusted GFBR is determined as a predicted service quality parameter.
  • the analysis and prediction function component can be extracted through the parameter prediction model
  • the corresponding parameter change feature W2 (related to the target site) can be obtained, and then it can be predicted that the PDB value of the QoS flow at the target site may be reduced based on the parameter change feature W2, then the current PDB value of the QoS flow can be adjusted to a lower value, then the adjusted PDB is determined as the predicted QoS parameter.
  • the analysis and prediction function component can send the predicted quality of service parameters generated by the prediction to the application client through the analysis and prediction interface, so the application client can adjust its business-related sending parameters (such as encoding rate, compression rate, etc.).
  • the analysis and prediction function component may also analyze and predict the overall performance change of the network slice to which the service flow on the terminal device belongs. Specifically, after the analysis and prediction function component on the terminal device receives the parameter prediction request, it can obtain the network slice selection auxiliary information (that is, S-NSSAI, Single Network Slice Selection ASSistance Information) associated with the application client according to the parameter prediction request.
  • the network slice selection auxiliary information that is, S-NSSAI, Single Network Slice Selection ASSistance Information
  • the network slice corresponding to the network slice selection auxiliary information, and further, based on the historical parameter information corresponding to the quality of service parameter associated with the network slice in the above quality of service parameter set, predict the predicted service corresponding to the quality of service flow A quality parameter, wherein the QoS parameter associated with the network slice includes the target QoS parameter, that is, the application client runs on the network slice.
  • the historical parameter information corresponding to the service quality parameter associated with the network slice can also be input into the pre-trained parameter prediction model, and the parameter change characteristics corresponding to the historical parameter information can be extracted through the parameter prediction model, and then based on the parameter
  • the change feature adjusts the QoS parameters associated with the network slice, so as to obtain the predicted QoS parameters corresponding to the QoS flow (and other QoS flows on the network slice).
  • the historical parameter information may include the overall performance change of the network slice to which the service flow on the application client belongs during the statistical time period, and the parameter change feature may indicate the influencing factors that may cause the change, such as environmental factors (time, place, etc.) etc.), connected data networks or network slices, etc.
  • the analysis and prediction function component can generate corresponding analysis and prediction results (that is, predicted service quality parameters) through the parameter prediction model.
  • the analysis and prediction function component on the terminal device can send the predicted quality of service parameters generated by the prediction to all application clients (including the above-mentioned application clients) running on the network slice through the analysis and prediction interface, and then these application clients The end can adjust the business data packets sent in relation to its business.
  • the parameter prediction method based on network slicing takes into account the higher-dimensional parameter change characteristics, and an appropriate parameter prediction method can be selected according to the actual situation. No limit.
  • the analysis and prediction function component on the terminal device can send the prediction service quality parameters to the application program client through the analysis and prediction interface.
  • the analysis and prediction function The component can generate a parameter prediction response message containing the predicted quality of service parameter, which can then be sent to the application client.
  • the application client After the application client receives the parameter prediction response message, it can analyze the parameter prediction response message to obtain the predicted service quality parameter, and then adjust the encoding algorithm used in the current streaming media service based on the predicted service quality parameter (such as adjusting the encoding rate, compression rate, etc.), so that an optimized service data packet can be generated based on the adjusted encoding algorithm and the streaming media data generated in the streaming media service, and when the optimized service data packet is to be uploaded to the server later, The terminal device can still map optimized service data packets to appropriate QoS flows based on QoS rules for transmission.
  • the streaming media service refers to a service of transmitting streaming media data such as audio, video, text, image, and animation in a streaming manner.
  • the application program client can generate optimized service data packets according to the predicted service quality parameters, so that the possibility that the optimized service data packets can meet future transmission requirements is increased, and the service quality of the streaming media service is improved.
  • the parameter prediction model can be integrated in the analysis and prediction function component, for example, it can be used as a functional module in the analysis and prediction function component to predict the corresponding prediction service quality parameter according to the historical parameter information, wherein the parameter prediction model can be It is an AI (Artificial Intelligence, artificial intelligence) model based on Deep Neural Networks (DNN for short), which can be obtained by training the initial parameter prediction model.
  • the sample parameter information (including initial service quality parameters, sample environment information and changing service quality parameters) obtained by collecting a large number of sample terminal devices can be input into the initial parameter prediction model, and then the initial parameter prediction model can be used to The feature extraction layer in the feature extraction layer extracts the initial service quality parameters and the sample parameter change characteristics corresponding to the sample environment information.
  • the corresponding sample prediction service quality parameters can be generated based on the sample parameter change characteristics , and then the sample prediction service quality parameters can be output, and then the loss function can be generated according to the sample prediction service quality parameters and the changing service quality parameters, and then the model parameters of the initial parameter prediction model can be adjusted based on the loss function until the model converges, and finally can be Get the trained parameter prediction model. Therefore, based on the historical parameter information, the parameter change characteristics can be accurately determined based on the historical parameter information through the parameter prediction model.
  • FIG. 4 is an interactive schematic diagram of a data processing process provided by an embodiment of the present application. As shown in Figure 4, the data processing process may include the following steps:
  • the application program client corresponding to the protocol data unit session on the terminal device will send an analysis and prediction parameter request (that is, a parameter prediction request) to the analysis and prediction Functional components (can provide analysis and prediction functions);
  • the analysis and prediction function component After the analysis and prediction function component receives the analysis and prediction parameter request through the analysis and prediction interface, it can determine which QoS flow or which network slice the service data flow of the application client belongs to, and send the QoS flow corresponding to the service flow of the application client Or the parameter prediction information of the network slice (that is, the predicted service quality parameter) is sent to the application program client.
  • the embodiment of the present application also provides a parameter prediction notification function, through which the application program client can be provided with predicted parameter change information.
  • a parameter prediction notification function through which the application program client can be provided with predicted parameter change information.
  • the embodiment of the present application can support the application client corresponding to the protocol data unit session on the terminal device to generate a parameter prediction request, and send the parameter prediction request to the analysis and prediction function component in the terminal device, and then the analysis and prediction function component can be based on the parameter
  • the prediction request is for the application client to predict the predicted QoS parameter corresponding to the QoS flow, and finally the predicted QoS parameter can be sent to the application client.
  • the analysis and prediction function component can respond to the parameter prediction request sent by the application program client running on the terminal device, and provide the application program client
  • the terminal predicts the corresponding quality of service parameters, so that the application client can make adaptive adjustments based on the predicted quality of service parameters, so that the ability of the application client to obtain and use the predicted quality of service parameters can be expanded in the quality of service mechanism, and Improve transmission efficiency.
  • FIG. 5 is a schematic flowchart of a data processing method provided by an embodiment of the present application.
  • the data processing method can be executed by a terminal device, and the terminal device includes an application program client and an analysis and prediction function component.
  • the data processing method may at least include the following steps:
  • the terminal device obtains the first function instruction issued by the network element of the mobile core network
  • the terminal device may acquire a first function instruction issued by a network element of the mobile core network, where the first function instruction is used to indicate whether the terminal device opens the analysis and prediction function of the analysis and prediction function component to the application program client, where the network element of the mobile core network may be a session management network element (or called a session management function), or other network elements, which is not limited in this application.
  • the network element of the mobile core network may be a session management network element (or called a session management function), or other network elements, which is not limited in this application.
  • the terminal device opens the analysis and prediction function of the analysis and prediction function component to the application program client is determined by the instruction of the mobile core network element, that is, the session management network element issues the service quality rule and the corresponding service quality to the terminal device.
  • the mobile core network element will further indicate whether to allow the analysis and prediction interface of the relevant QoS flow or network slice to be called by the application client.
  • the analysis and prediction function component obtains the parameter prediction request sent by the application program client corresponding to the protocol data unit session;
  • the analysis and prediction function component predicts the predicted service quality parameters corresponding to the service quality flow for the application client based on the parameter prediction request, and sends the predicted service quality parameters to the application client;
  • the analysis and prediction function component can predict the prediction corresponding to the quality of service flow for the application client based on the parameter prediction request QoS parameters, and send the predicted QoS parameters to the application program client, wherein, the specific process of predicting the QoS parameters corresponding to the QoS flow and sending them to the application program client can refer to the above-mentioned embodiment corresponding to FIG. 3 S102 in , will not be repeated here.
  • the function opening instruction may instruct the terminal device to open the analysis and prediction function of the analysis and prediction function component to the application program client.
  • the application client signs a parameter prediction notification function with the analysis and prediction function component.
  • the analysis and prediction function component predicts that the target service quality parameter has a change trend or the predicted service quality parameter exceeds the threshold value, it notifies the application based on the parameter prediction notification function.
  • the application client on the terminal device can subscribe the parameter prediction notification function to the analysis and prediction function component through the analysis and prediction interface.
  • the analysis and prediction function component predicts that the target service quality
  • a parameter change notification message can be generated based on the parameter prediction notification function, and then the parameter change notification message can be sent to the application program client through the analysis and prediction interface, and then the application program client can renew based on the parameter change notification message.
  • a parameter prediction request is initiated to the analysis and prediction function component, and then the re-predicted QoS parameters can be sent to the application program client through the analysis and prediction interface through a process similar to that described in the above embodiment corresponding to FIG. 3 .
  • the application program client may further include parameter information such as the maximum number of notifications and the threshold value corresponding to the predicted quality of service parameter in the subscription request.
  • the threshold value can be set according to business requirements, and this application does not limit the specific size of the threshold value.
  • the analysis and prediction function component does not need to notify through the parameter prediction notification function as soon as the relevant change trend is predicted, but to notify when the predicted service quality parameter exceeds the threshold value, which can reduce the impact of frequent notifications.
  • the interference of the application client reduces the data interaction between the application client and the analysis and prediction function components.
  • the application client can first initiate a parameter prediction request to the analysis and prediction function component through the analysis and prediction interface to obtain the prediction service quality parameters, and the application client sends the analysis and prediction After the functional component signs the parameter prediction notification function, when the target service quality parameter is predicted to have a changing trend or the predicted service quality parameter exceeds the threshold value, the analysis and prediction function component can actively send it to the application client based on the parameter prediction notification function.
  • the predicted QoS parameter or notification information ie parameter change notification message
  • the analysis and prediction function component sends request rejection information to the application program client.
  • the request rejection information is for the aforementioned parameter prediction request.
  • the analysis and prediction function component can send a request rejection to the application client through the analysis and prediction interface.
  • the function disabling instruction is used to instruct the terminal device not to open the analysis and prediction function of the analysis and prediction function component to the application client (or not to open the analysis and prediction interface to the application client).
  • the request rejection information may include a rejection reason identifier (also referred to as a rejection reason value), where the rejection reason identifier is used to represent a rejection reason for the parameter prediction request, and is predefined by the network.
  • the analysis and prediction function component receives the parameter prediction request (also called the analysis and prediction parameter request) sent by the application program client.
  • the parameter prediction request also called the analysis and prediction parameter request
  • a rejection of the request is indicated in the corresponding response message, and may further include a rejection reason value.
  • the terminal device can accurately determine which application program clients to open the analysis and prediction function and which application program clients to close the analysis and prediction function, which improves the efficiency of effective analysis and prediction.
  • the mobile core network element indicates whether the open analysis and prediction interface is allowed to be called by the application program client
  • one or more of the following function indication information may be considered: subscription information of the terminal device, protocol data unit when the session is initiated Carried data network name (DNN) and single network slice selection auxiliary information (S-NSSAI), operator's own configuration, network policy, etc.
  • DNN Carried data network name
  • S-NSSAI single network slice selection auxiliary information
  • operator's own configuration e.g., operator's own configuration
  • network policy e.g., a service that specifies a specific network slice
  • the service may allow an analysis and prediction interface to be opened, and the embodiment of the present application does not limit the permission policy specifically adopted by the network element of the mobile core network.
  • the mobile core network element by sending the second function instruction to the mobile core network element through the terminal device, the mobile core network element can be accurately notified of the support status of the terminal device for the analysis and prediction function, so that the mobile core network element can be based on the terminal device According to the support status, the first function instruction is selectively sent to the terminal equipment supporting the quality of service interface, which reduces the possibility of invalidly sending the first function instruction (for example, sending to the terminal equipment that does not support the analysis and prediction function), and improves the interaction efficiency.
  • FIG. 6 is an interactive schematic diagram of a parameter prediction notification process provided by an embodiment of the present application. As shown in Figure 6, the process may include the following steps:
  • the application client subscribes to the analysis and prediction function component (or called UE analysis and prediction function module) for notification of analysis and prediction parameters (ie parameter prediction notification function);
  • the analysis and prediction function component or called UE analysis and prediction function module
  • the analysis and prediction function component can notify the application program client through the analysis and prediction interface.
  • the application client does not need to frequently send parameter prediction requests to the analysis and prediction function components, but can change when the relevant service quality parameters may change, or the predicted service quality parameters exceed the threshold value, or when the corresponding analysis and prediction results are generated, the application client is actively notified of the possible changes in the quality of service parameters through the analysis and prediction interface, or the obtained analysis and prediction results are directly sent, or the predicted quality of service parameters exceed the threshold Value notification information, so that the application client can directly perceive the possible changes of the quality of service parameters, and improve the acquisition efficiency of the predicted quality of service parameters.
  • FIG. 7 is a schematic flowchart of a data processing method provided by an embodiment of the present application.
  • the data processing method can be executed by a terminal device, and the terminal device includes an application program client and an analysis and prediction function component.
  • the data processing method may at least include the following steps:
  • the terminal device sends a second function instruction to a mobile core network element
  • a terminal device when a terminal device initiates a PDU session, it may indicate to the network element of the mobile core network whether the terminal device supports the analysis and prediction function of the analysis and prediction function component, that is, send a second function instruction to the network element of the mobile core network.
  • the second function instruction can be used as a parameter in the N1SM container.
  • the second function instruction sent by the terminal device is a function support instruction, that is, when the terminal device clearly indicates that it supports the analysis and prediction function of the analysis and prediction function component
  • S502 can be continued;
  • the instruction is supported (that is, the terminal device indicates that it does not support the analysis and prediction function of the prediction function component), or the terminal device does not indicate that it supports the analysis and prediction function of the prediction function component (that is, the mobile core network element will think that the terminal device does not need or does not support the analysis and prediction function of the prediction function component)
  • the network element of the mobile core network may be a session management network element or other network elements, which is not limited in this application.
  • the terminal device obtains the first function instruction issued by the network element of the mobile core network;
  • the mobile core network element when it detects that the second function instruction is a function support instruction, it can generate the first function instruction based on the permission policy, and send the first function instruction to the terminal device, and then the terminal device can receive the first function instruction. instruction.
  • the terminal device can receive the first function instruction. instruction.
  • the analysis and prediction function component obtains the parameter prediction request sent by the application program client corresponding to the PDU session;
  • the analysis and prediction function component predicts the predicted service quality parameters corresponding to the service quality flow for the application client based on the parameter prediction request, and sends the predicted service quality parameters to the application client;
  • the analysis and prediction function component sends request rejection information to the application client;
  • the application client subscribes the parameter prediction notification function to the analysis and prediction function component, and when the analysis and prediction function component predicts that the target service quality parameter has a change trend or the predicted service quality parameter exceeds the threshold value, based on the parameter prediction notification function, notify the application program client.
  • the analysis and prediction function component predicts When the target quality of service parameter has a change trend, it is also possible to re-predict the possible change of the service quality parameter for the application client, or when the predicted service quality parameter exceeds the threshold value, notify the application client, so that the subsequent application
  • the client can make adaptive adjustments based on the predicted QoS parameters, so that the ability of the application client to obtain and use the predicted QoS parameters can be expanded in the QoS mechanism.
  • FIG. 8 is a schematic flowchart of a data processing method provided in an embodiment of the present application.
  • the data processing method can be executed by a terminal device, and the terminal device includes an application program client and an analysis and prediction function component.
  • the data processing method may at least include the following steps:
  • the application client signs a parameter prediction notification function for the protocol data unit session with the analysis and prediction function component; the protocol data unit session is associated with the service data packet provided by the application client;
  • the application client can subscribe to the analysis and prediction function component through the analysis and prediction interface for the parameter prediction notification function for the session of the protocol data unit.
  • the analysis and prediction function component can provide the application client with the predicted service quality parameter .
  • the application client runs in the terminal device, and the protocol data unit session is associated with the service data package provided by the application client.
  • the analysis and prediction function component predicts the predicted service quality parameters corresponding to the service quality flow for the application client based on the parameter prediction notification function; the service quality flow is associated with the service data packet;
  • the analysis and prediction function component on the terminal device can predict the predicted service quality parameters corresponding to the service quality flow for the application client based on the parameter prediction notification function, wherein the service quality flow and the service data provided by the application client package is associated.
  • the analysis and prediction function component can identify the QoS flow corresponding to the QoS flow ID based on the QoS flow ID associated with the application program client, and then can based on The historical parameter information corresponding to the target QoS parameter predicts the predicted QoS parameter corresponding to the QoS flow.
  • the analysis and prediction function component can identify the network slice corresponding to the single network slice selection auxiliary information based on the single network slice selection auxiliary information associated with the application client, and then can based on the service
  • the historical parameter information corresponding to the QoS parameter associated with the network slice in the quality parameter set predicts the predicted QoS parameter corresponding to the QoS flow.
  • the analysis and prediction function component sends the predicted service quality parameter to the application program client; the target service quality parameter is provided by the session management network. Issued by Yuan.
  • the analysis and prediction function component on the terminal device can compare the predicted service quality parameter with the target service quality parameter issued by the session management network element, when the predicted service quality parameter and the target service quality parameter (that is, the actual service quality parameters) are different, the analysis and prediction interface can be called through the parameter prediction notification function, and then the prediction service quality parameter or the notification information that the prediction service quality parameter exceeds the threshold value can be sent to the application program client through the analysis and prediction interface.
  • the analysis and prediction interface can be called through the parameter prediction notification function, and then the prediction service quality parameter or the notification information that the prediction service quality parameter exceeds the threshold value can be sent to the application program client through the analysis and prediction interface.
  • the analysis and prediction interface can be called through the parameter prediction notification function, and then the prediction service quality parameter or the notification information that the prediction service quality parameter exceeds the threshold value can be sent to the application program client through the analysis and prediction interface.
  • the analysis and prediction interface can be called through the parameter prediction notification function, and then the prediction service quality parameter or the notification information that the prediction service quality parameter exceeds the threshold
  • the analysis and prediction function component can calculate the corresponding confidence of the predicted service quality parameter, if the confidence is greater than the comparison Threshold, it can be considered that the predicted service quality parameter is different from the target service quality parameter, that is, it is predicted that the target service quality parameter is likely to change (with a large change trend), and the comparison threshold can be set according to actual needs.
  • the embodiment of the application does not limit this.
  • the function of subscription parameter prediction and notification can support the analysis and prediction function component to proactively predict relevant service quality parameters for the application program client, so that the application program client can follow up based on the predicted service quality parameters.
  • Adaptive adjustment so that the ability of the application client to obtain and use the predicted quality of service parameters can be expanded in the quality of service mechanism.
  • FIG. 9 is a schematic flowchart of a data processing method provided by an embodiment of the present application.
  • the data processing method can be jointly executed by a session management network element, a terminal device (including an analysis and prediction function component), and an application program client running on the terminal device.
  • the data processing method may at least include the following steps:
  • the session management network element may deliver a QoS rule and a QoS parameter set to the terminal device.
  • the terminal device After receiving the quality of service rule and the quality of service parameter set, the terminal device can map the service data packet sent by the application program client corresponding to the protocol data unit session to the quality of service flow based on the quality of service rule.
  • the specific process can be referred to above. S102 in the embodiment corresponding to FIG. 3 will not be repeated here.
  • the terminal device may generate a second function instruction and send it to the session management network element, so as to indicate to the session management network element whether the terminal device supports the analysis and prediction function of the analysis and prediction function component.
  • the session management network element may judge the second function instruction. If the second function instruction is a function support instruction, the session management network element may generate the first function instruction based on the function indication information, where the function indication information includes but is not limited to the subscription information of the terminal equipment, the data carried when the protocol data unit session is initiated One or more of network name and single network slice selection auxiliary information, operator's own configuration, and network policy.
  • the first function instruction may be a function opening instruction or a function closing instruction.
  • the session management network element may not generate the first function instruction.
  • the session management network element may deliver the generated first function instruction to the terminal device.
  • the application client may send a parameter prediction request to the analysis and prediction function component on the terminal device.
  • the terminal device may first judge the first function instruction. If the first function instruction is a function opening instruction, the analysis and prediction function component may predict the QoS parameter corresponding to the QoS flow for the application client. For the specific process, refer to S303 in the above embodiment corresponding to FIG. 5 .
  • the analysis and prediction function component on the terminal device can send the predicted service quality parameter to the application program client through the analysis and prediction interface.
  • the analysis and prediction function component on the terminal device may generate request rejection information.
  • the request rejection message is for a parameter prediction request.
  • the analysis and prediction function component on the terminal device may send request rejection information to the application program client through the analysis and prediction interface.
  • the application program client may sign a parameter prediction notification function with the analysis and prediction function component.
  • the analysis and prediction function component on the terminal device may re-predict the corresponding service quality parameter for the application client based on the parameter prediction notification function, Alternatively, the notification information that the predicted service quality parameter exceeds the threshold value is sent to the application program client.
  • the analysis and prediction function component on the terminal device may deliver the re-predicted QoS parameters to the terminal device through the analysis and prediction interface.
  • the analysis and prediction functional component may first send a parameter change notification message to the application program client, and then the application program client may re-initiate a parameter prediction request based on the parameter change notification message, and finally obtain the re-predicted QoS parameter.
  • the analysis and prediction function component predicts that the target service quality parameter has a change trend or the predicted service quality parameter exceeds the threshold value, it can also re-predict the possible change of the service quality parameter for the application client, so that the subsequent application
  • the client can make adaptive adjustments based on the predicted QoS parameters, so that the ability of the application client to obtain and use the predicted QoS parameters can be expanded in the QoS mechanism.
  • FIG. 10 is a schematic structural diagram of a data processing device provided by an embodiment of the present application.
  • the data processing device may be a computer program (including program code) running on a computer device, for example, the data processing device is an application software; the device may be used to execute the corresponding steps in the data processing method provided by the embodiment of the present application.
  • the data processing apparatus 1 may run on a terminal device, and the terminal device may be the terminal device A in the above-mentioned embodiment corresponding to FIG. 2 .
  • the data processing 1 may include: a request sending module 11, an analysis and prediction function module 12;
  • the request sending module 11 is used to send the parameter prediction request to the analysis and prediction function module 12; the parameter prediction request is generated by the application client; the application client runs in the terminal device;
  • the analysis and prediction function module 12 is used to predict the QoS parameter corresponding to the QoS flow for the application program client based on the parameter prediction request, and send the QoS parameter prediction to the application program client; Provided business data packages are associated.
  • the analysis and prediction function module 12 here is the analysis and prediction function component in the above-mentioned embodiment corresponding to FIG. 3 .
  • the data processing device 1 may further include: a mapping module 13;
  • the mapping module 13 is configured to receive the QoS rule and the QoS parameter set issued by the session management network element, and map the service data packet sent by the application program client to the QoS flow based on the QoS rule; the QoS parameter set includes The target QoS parameter associated with the QoS flow.
  • mapping module 13 For the implementation of the specific functions of the mapping module 13, refer to S102 in the above embodiment corresponding to FIG. 3 , which will not be repeated here.
  • the data processing device 1 may also include: a notification signing module 14 and a re-requesting module 15;
  • the above analysis and prediction function module 12 is also used to generate a parameter change notification message based on the parameter prediction notification function when it is predicted that the target service quality parameter has a change trend or the predicted service quality parameter exceeds the threshold value, and send the parameter change notification message to application client;
  • the re-request module 15 is configured to send a parameter prediction request; the parameter prediction request is regenerated by the application program client based on the parameter change notification message.
  • the data processing device 1 may further include: an instruction acquisition module 16;
  • An instruction acquiring module 16 configured to acquire the first functional instruction issued by the mobile core network element
  • the above analysis and prediction function module 12 is also used for if the first function instruction is a function opening instruction, then perform the step of predicting the service quality parameter corresponding to the application program client’s prediction service quality flow based on the parameter prediction request; the function opening instruction indicates The terminal device opens the analysis and prediction function of the analysis and prediction function module 12 to the application client.
  • the aforementioned mobile core network element may be a session management element.
  • the above-mentioned analysis and prediction function module 12 is also used to send request rejection information for the parameter prediction request to the application program client if the first function instruction is a function shutdown instruction; the function shutdown instruction indicates that the terminal device does not The analysis and prediction function of the analysis and prediction function module 12 is opened to the application client.
  • the data processing device 1 may also include: a function support module 17;
  • the function support module 17 is used to send the second function instruction to the network element of the mobile core network; if the second function instruction is a function support instruction, then perform the step of obtaining the first function instruction issued by the network element of the mobile core network; the function support The instruction instructs the terminal device to support the analysis and prediction function of the analysis and prediction function module 12 .
  • the specific function implementation manner of the interface support module 17 can refer to S501 in the above embodiment corresponding to FIG. 7 , which will not be repeated here.
  • the above analysis and prediction function module 12 may include: a first identification unit 121, a first prediction unit 122, and a first sending unit 123;
  • the first identifying unit 121 is configured to acquire the QoS flow identifier associated with the application program client according to the parameter prediction request, and identify the QoS flow corresponding to the QoS flow identifier;
  • the first prediction unit 122 is configured to predict the predicted QoS parameter corresponding to the QoS flow based on the historical parameter information corresponding to the target QoS parameter;
  • the above-mentioned first prediction unit 122 is specifically configured to input the historical parameter information corresponding to the target quality of service parameter into the parameter prediction model, extract the parameter change characteristics corresponding to the historical parameter information through the parameter prediction model, and adjust the target service quality parameter based on the parameter change characteristics , to obtain the predicted service quality parameters corresponding to the service quality flow;
  • the first sending unit 123 is configured to send the predicted service quality parameter to the application program client;
  • the application client is a client that executes a streaming media service
  • the first sending unit 123 is specifically configured to send a parameter prediction response message including a predicted quality of service parameter to the application program client, so that the application program client can adjust the encoding algorithm based on the predicted service quality parameter, and based on the adjusted encoding algorithm As well as streaming media data, an optimized business data package is generated.
  • the above analysis and prediction function module 12 may include: a second identification unit 124, a second prediction unit 125, and a second sending unit 126;
  • the second identifying unit 124 is configured to acquire the network slice selection auxiliary information associated with the application client according to the parameter prediction request, and identify the network slice corresponding to the network slice selection auxiliary information;
  • the second prediction unit 125 is configured to predict the predicted QoS parameter corresponding to the QoS flow based on the historical parameter information corresponding to the QoS parameter associated with the network slice in the QoS parameter set; the QoS parameter associated with the network slice includes the target service quality parameters;
  • the second sending unit 126 is configured to send the predicted service quality parameter to the application program client;
  • the application client is a client that executes a streaming media service
  • the second sending unit 126 is specifically configured to send a parameter prediction response message including a predicted quality of service parameter to the application program client, so that the application program client can adjust the encoding algorithm based on the predicted service quality parameter, and based on the adjusted encoding algorithm As well as streaming media data, an optimized business data package is generated.
  • the embodiment of the present application can support the application client corresponding to the protocol data unit session on the terminal device to send a parameter prediction request to the analysis and prediction function component, and then the analysis and prediction function component can predict the quality of service flow for the application client based on the parameter prediction request.
  • the corresponding predicted QoS parameter can finally send the predicted QoS parameter to the application program client.
  • the analysis and prediction function component can respond to the parameter prediction request sent by the application program client running on the terminal device, and predict the corresponding service quality parameters for the application program client, so that the subsequent application program client can be based on
  • the predicted service quality parameters are adaptively adjusted, so that the ability of the application program client to obtain and use the predicted service quality parameters can be expanded in the service quality mechanism.
  • FIG. 11 is a schematic structural diagram of a data processing device provided by an embodiment of the present application.
  • the data processing device may be a computer program (including program code) running on a computer device, for example, the data processing device is an application software; the device may be used to execute the corresponding steps in the data processing method provided by the embodiment of the present application.
  • the data processing apparatus 2 may run on a terminal device, and the terminal device may be the terminal device A in the above-mentioned embodiment corresponding to FIG. 2 .
  • the data processing 2 may include: a signing module 21, an analysis and prediction function module 22;
  • the signing module 21 is used to sign a parameter prediction notification function associated with the application client to the analysis and prediction function module; the application client is the client corresponding to the protocol data unit session, and the application client runs in the terminal device;
  • the analysis and prediction function module 22 is used to predict the service quality parameters corresponding to the service quality flow for the application program client based on the parameter prediction notification function; the service quality flow is associated with the service data package provided by the application program client;
  • the analysis and prediction function module 22 is also used for sending the predicted quality of service parameter to the application program client when the predicted service quality parameter is different from the target quality of service parameter or when the predicted service quality parameter exceeds the threshold value; the target service quality parameter is determined by Issued by the session management NE.
  • the specific function implementation of the signing module 21 can refer to S601 in the above-mentioned embodiment corresponding to FIG. Let me repeat.
  • the analysis and prediction function module 22 here is the analysis and prediction function component in the above-mentioned embodiment corresponding to FIG. 8 .
  • the function of subscription parameter prediction and notification can support the analysis and prediction function component to proactively predict relevant service quality parameters for the application program client, so that the application program client can follow up based on the predicted service quality parameters.
  • Adaptive adjustment so that the ability of the application client to obtain and use the predicted quality of service parameters can be expanded in the quality of service mechanism.
  • FIG. 12 is a schematic structural diagram of a network element device provided by an embodiment of the present application.
  • the network element device can be a computer program (including program code) running on the network element equipment, for example, the network element device is an application software; the device can be used to execute the corresponding steps in the data processing method provided by the embodiment of the present application .
  • the network element device 3 may run on a session management network element.
  • the network element device 3 may include: a delivery module 31;
  • the delivery module 31 is configured to deliver a quality of service rule and a quality of service parameter set to the terminal device, so that the terminal device maps the service data packet sent by the application program client corresponding to the protocol data unit session to the service based on the quality of service rule Quality flow; the terminal device includes an application client and an analysis and prediction function component.
  • the application client has the function of generating a parameter prediction request, and the parameter prediction request instructs the analysis and prediction function component to send the predicted service quality parameters corresponding to the service quality flow to the application program
  • the predicted QoS parameter is obtained by the analysis and prediction function component based on the parameter prediction request to predict the service data packet;
  • the QoS parameter set includes the target QoS parameter.
  • the network element device 3 may also include: an instruction generating module 32;
  • the instruction generation module 32 is used to generate a first function instruction based on the function indication information, and issue the first function instruction to the terminal device;
  • the first function instruction is a function opening instruction or a function closing instruction;
  • the function opening instruction instructs the terminal device to send the application program
  • the client opens the analysis and prediction function of the analysis and prediction function component;
  • the function closing instruction instructs the terminal device not to open the analysis and prediction function of the analysis and prediction function component to the application program client.
  • the network element device 3 may further include: an instruction acquisition module 33;
  • the instruction acquisition module 33 is used to acquire the second function instruction sent by the terminal device; if the second function instruction is a function support instruction, perform the step of generating the first function instruction based on the function instruction information; the function support instruction indicates that the terminal device supports analysis and prediction Analysis and forecasting functions of functional components.
  • the analysis and prediction function component predicts that the target service quality parameter has a change trend or the predicted service quality parameter exceeds the threshold value, it can also re-predict the possible change of the service quality parameter for the application client, so that the subsequent application
  • the client can make adaptive adjustments based on the predicted QoS parameters, so that the ability of the application client to obtain and use the predicted QoS parameters can be expanded in the QoS mechanism.
  • the computer device 1000 may include: a processor 1001 , a network interface 1004 and a memory 1005 .
  • the computer device 1000 may further include: a user interface 1003 and at least one communication bus 1002 .
  • the communication bus 1002 is used to realize connection and communication between these components.
  • the user interface 1003 may include a display screen (Display) and a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.
  • the network interface 1004 may include a standard wired interface and a wireless interface (such as a WI-FI interface).
  • the memory 1004 can be a high-speed RAM memory, or a non-volatile memory, such as at least one disk memory.
  • the memory 1005 may also be at least one storage device located away from the aforementioned processor 1001 .
  • the memory 1005 as a computer-readable storage medium may include an operating system, a network communication module, a user interface module, and a device control application program.
  • the computer device 1000 may be a terminal device.
  • the network interface 1004 can provide network communication functions; and the user interface 1003 is mainly used to provide an input interface for the user; and the processor 1001 can be used to call the device control stored in the memory 1005 Application program, so that the computer device 1000 executes the description of the data processing method in any one of the embodiments corresponding to Figure 3, Figure 5, Figure 7, Figure 8, and Figure 9 above, and can also execute the embodiment corresponding to Figure 10 above
  • the description of the data processing device 1 in , or the data processing device 2 in the embodiment corresponding to FIG. 11 will not be repeated here.
  • the description of the beneficial effect of adopting the same method will not be repeated here.
  • the network element device 2000 may include: a processor 2001 , a network interface 2003 and a memory 2004 .
  • the network element device 2000 may further include: at least one communication bus 2002 .
  • the communication bus 2002 is used to realize connection and communication between these components.
  • the network interface 2003 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).
  • the memory 2004 can be a high-speed RAM memory, or a non-volatile memory, such as at least one disk memory.
  • the memory 2004 may also be at least one storage device located away from the aforementioned processor 2001 .
  • the memory 2004 as a computer-readable storage medium may include an operating system, a network communication module, and a device control application program.
  • the network element device 2000 may be a session management network element.
  • the network interface 2003 can provide network communication functions; and the processor 2001 can be used to call the device control application program stored in the memory 2004, so that the network element device 2000 executes the preceding figure
  • the description of the data processing method in the embodiment corresponding to FIG. 9 may also execute the description of the network element device 3 in the embodiment corresponding to FIG. 12 above, and details are not repeated here.
  • the description of the beneficial effect of adopting the same method will not be repeated here.
  • the embodiment of the present application also provides a computer-readable storage medium, and the above-mentioned computer-readable storage medium stores the aforementioned data processing device 1 or data processing device 2 or network element device 3.
  • the computer program executed, and the above computer program includes program instructions.
  • the above processor executes the above program instructions, it can execute the above-mentioned embodiment corresponding to any one of FIG. 3 , FIG. 5 , FIG. 7 , FIG. 8 , and FIG. 9
  • the description of the above data processing method therefore, will not be repeated here.
  • the description of the beneficial effect of adopting the same method will not be repeated here.
  • the technical details not disclosed in the embodiments of the computer-readable storage medium involved in the present application please refer to the description of the method embodiments of the present application.
  • the foregoing computer-readable storage medium may be the data processing device or network element device provided in any of the foregoing embodiments, or an internal storage unit of the foregoing computer device or network element device, such as a hard disk or memory of the computer device.
  • the computer-readable storage medium may also be an external storage device of the computer device (or network element device), such as a plug-in hard disk equipped on the computer device, a smart memory card (smart media card, SMC), a secure digital (secure digital, SD) card, flash card (flash card), etc.
  • the computer-readable storage medium may also include both an internal storage unit of the computer device (or network element device) and an external storage device.
  • the computer-readable storage medium is used to store the computer program and other programs and data required by the computer device (or network element device).
  • the computer-readable storage medium can also be used to temporarily store data that has been output or will be output.
  • the embodiment of the present application also provides a computer program product or computer program, where the computer program product or computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium.
  • the processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes any one of the embodiments corresponding to Figure 3, Figure 5, Figure 7, Figure 8, and Figure 9 above provided method.
  • the processor of the network element device may also read the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the network element device executes the method provided in the embodiment corresponding to FIG. 9 above.
  • FIG. 15 is a schematic structural diagram of a data processing system provided by an embodiment of the present application.
  • the data processing system 4 may include a data processing device 1a, a data processing device 2a, and a network element device 3a.
  • the data processing device 1a may be the data processing device 1 in the above-mentioned embodiment corresponding to FIG. 10. It can be understood that the data processing device 1a may be integrated into the terminal device A in the above-mentioned embodiment corresponding to FIG. 2, therefore, No further details will be given here.
  • the data processing device 2a may be the data processing device 2 in the above-mentioned embodiment corresponding to FIG. 11.
  • the data processing device 2a may be integrated into the terminal device A in the above-mentioned embodiment corresponding to FIG. 2, therefore, No further details will be given here.
  • the network element device 3a may be the network element device 3 in the above-mentioned embodiment corresponding to FIG. 12 , therefore, details will not be repeated here.
  • the description of the beneficial effect of adopting the same method will not be repeated here.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Quality & Reliability (AREA)
  • Computer Security & Cryptography (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本申请公开了一种数据处理方法、设备、可读存储介质和程序产品，该方法由终端设备执行，终端设备包括应用程序客户端和分析预测功能组件，该方法包括：协议数据单元会话对应的应用程序客户端生成参数预测请求，将参数预测请求发送至分析预测功能组件；分析预测功能组件基于参数预测请求为应用程序客户端预测服务质量流所对应的预测服务质量参数，将预测服务质量参数发送至应用程序客户端；服务质量流与应用程序客户端所提供的业务数据包相关联。采用本申请，可以在服务质量机制中拓展应用程序客户端感知预测服务质量参数的能力。

Description

一种数据处理方法、设备、可读存储介质和程序产品
本申请要求于2021年09月10日提交中国专利局、申请号为202111061875.9、申请名称为“一种数据处理方法、设备以及可读存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及通信技术领域，尤其涉及数据处理。
背景技术
随着智能终端的普及和快速发展，为满足用户对不同应用不同服务质量的要求，就需要网络能根据业务的需求分配和调度资源，对不同的业务流提供不同的服务质量。因此，服务质量(Quality of Service，QoS)应运而生。QoS指一个网络能够利用各种基础技术，为指定的网络通信提供所需服务的能力，QoS是网络的一种服务质量保障机制，可用于保障网络延迟、误码率、数据传输速率等，依据QoS更加合理地利用网络资源。
目前，在第五代移动通信技术(5th Generation Mobile Communication Technology，简称5G)中，为了保证业务端到端的服务质量，提出了5G QoS模型。5G QoS模型基于QoS流(QoS Flow)，可以支持保证流比特率的QoS流(Guaranteed Bit Rate QoS Flow，GBR QoS Flow)和不需要保证流比特率的QoS流(Non-GBR QoS Flow)。在相关技术中，5G核心网中的会话管理网元(SeSSion Management Function，SMF)会根据策略控制网元(Policy Control Function，PCF)发送的策略控制和计费(Policy Control and Charging，PCC)规则生成QoS规则(QoS rule)，当协议数据单元会话(Protocol Data Unit SeSSion，PDU SeSSion)建立时，SMF会将QoS规则发送给终端设备(User Equipment，UE)，同时也会发送流级别的QoS参数给UE，例如，对于GBR QoS流，可以包括分别针对上行链路(Uplink，UL)和下行链路(Downlink，DL)的保证流比特率(Guaranteed Flow Bit Rate，GFBR)、最大流比特率(Maximum Flow Bit Rate，MFBR)或可选的平均窗口(Averaging Window)等QoS参数。UE接收到QoS规则和QoS参数后，对于上行的业务流，可以应用该QoS规则将UE上的应用程序客户端提供的业务数据包映射到相应的QoS流。此外，5G系统还支持可替代QoS配置的机制，即SMF可以提供替代QoS配置文件(Alternative QoS Profile)给无线接入网络(Radio AcceSS Network，RAN)，当RAN侧无法满足现有的QoS参数时，会检测是否可以满足某个替代QoS配置文件中定义的QoS参数(例如保证流比特率、误包率、包延迟预算等)，如果可以满足，则RAN会发送相关通知给SMF，SMF则会进一步更新相应的QoS参数并发送给UE。
由此可知，相关技术方案中，只是涉及到网络侧的QoS参数的调整，但是对于UE上的应用程序客户端来说，应用程序客户端完全感知不到QoS参数及其变化情况。
发明内容
有鉴于此，本申请实施例提供了一种数据处理方法、设备、可读存储介质和程序产品，可以在服务质量机制中拓展应用程序客户端感知预测服务质量参数的能力。
本申请实施例一方面提供了一种数据处理方法，该方法由终端设备执行，该终端设备包括应用程序客户端和分析预测功能组件，该方法包括：
应用程序客户端生成参数预测请求，将参数预测请求发送至分析预测功能组件；
分析预测功能组件基于参数预测请求，为应用程序客户端预测服务质量流所对应的预测服务质量参数，将预测服务质量参数发送至应用程序客户端；服务质量流与应用程序客户端所提供的业务数据包相关联。
本申请实施例一方面提供了一种数据处理方法，该方法由终端设备执行，该终端设备包括应用程序客户端和分析预测功能组件，该方法包括：
应用程序客户端向分析预测功能组件签约针对协议数据单元会话的参数预测通知功能；协议数据单元会话与应用程序客户端提供的业务数据包相关联；
分析预测功能组件基于参数预测通知功能为应用程序客户端预测服务质量流所对应的预测服务质量参数；服务质量流与业务数据包相关联；
当预测服务质量参数与服务质量流相关联的服务质量参数不相同或者预测服务质量参数超过门限值时，分析预测功能组件将预测服务质量参数发送至应用程序客户端；服务质量流相关联的服务质量参数是由会话管理网元所下发的。
本申请实施例一方面提供了一种数据处理方法，包括：
会话管理网元向终端设备下发服务质量规则以及服务质量参数集，以使终端设备基于服务质量规则，将应用程序客户端所发送的业务数据包映射至服务质量流；终端设备包括应用程序客户端和分析预测功能组件，应用程序客户端具有生成参数预测请求的功能，参数预测请求指示分析预测功能组件将服务质量流对应的预测服务质量参数发送至应用程序客户端，预测服务质量参数是由分析预测功能组件基于参数预测请求为业务数据包所预测得到的；服务质量参数集包括与服务质量流相关联的服务质量参数。
本申请实施例一方面提供了一种数据处理装置，该装置运行在终端设备中，包括：
请求发送模块，用于将参数预测请求发送至分析预测功能模块；参数预测请求是由协议数据单元会话对应的应用程序客户端生成的；应用程序客户端运行在终端设备中；
分析预测功能模块，用于基于参数预测请求为应用程序客户端预测服务质量流所对应的预测服务质量参数，将预测服务质量参数发送至应用程序客户端；服务质量流与应用程序客户端所提供的业务数据包相关联。
本申请实施例一方面提供了一种数据处理装置，该装置运行在终端设备中，包括：
签约模块，用于向分析预测功能模块签约与应用程序客户端相关联的参数预测通知功能；应用程序客户端为协议数据单元会话对应的客户端，应用程序客户端运行于终端设备中；
分析预测功能模块，用于基于参数预测通知功能为应用程序客户端预测服务质量流所对应的预测服务质量参数；服务质量流与应用程序客户端提供的业务数据包相关联；
上述分析预测功能模块，还用于当预测服务质量参数与服务质量流相关联的服务质量参数不相同或者预测服务质量参数超过门限值时，将预测服务质量参数发送至应用程序客户端；服务质量流相关联的服务质量参数是由会话管理网元所下发的。
本申请实施例一方面提供了一种网元装置，该装置运行在会话管理网元中，包括：
下发模块，用于向终端设备下发服务质量规则以及服务质量参数集，以使终端设备基 于服务质量规则，将协议数据单元会话对应的应用程序客户端所发送的业务数据包映射至服务质量流；终端设备包括应用程序客户端和分析预测功能组件，应用程序客户端具有生成参数预测请求的功能，参数预测请求指示分析预测功能组件将服务质量流对应的预测服务质量参数发送至应用程序客户端，预测服务质量参数是由分析预测功能组件基于参数预测请求为业务数据包所预测得到的；服务质量参数集包括与服务质量流相关联的服务质量参数。
本申请实施例一方面提供了一种计算机设备，包括：处理器、存储器、网络接口；
上述处理器与上述存储器、上述网络接口相连，其中，上述网络接口用于提供数据通信功能，上述存储器用于存储计算机程序，上述处理器用于调用上述计算机程序，以使该计算机设备执行本申请实施例中的方法。
本申请实施例一方面提供了一种网元设备，包括：处理器、存储器、网络接口；
上述处理器与上述存储器、上述网络接口相连，其中，上述网络接口用于提供数据通信功能，上述存储器用于存储计算机程序，上述处理器用于调用上述计算机程序，以使该网元设备执行本申请实施例中的方法。
本申请实施例一方面提供了一种计算机可读存储介质，上述计算机可读存储介质中存储有计算机程序，上述计算机程序适于由处理器加载并执行本申请实施例中的方法。
本申请实施例一方面提供了一种计算机程序产品或计算机程序，该计算机程序产品或计算机程序包括计算机指令，该计算机指令存储在计算机可读存储介质中，计算机设备或网元设备的处理器从计算机可读存储介质读取该计算机指令，处理器执行该计算机指令，使得该计算机设备或该网元设备执行本申请实施例中的方法。
本申请实施例可以支持终端设备上应用程序客户端生成参数预测请求，并将参数预测请求发送至该终端设备中的分析预测功能组件，进而分析预测功能组件可以基于该参数预测请求，为应用程序客户端预测服务质量流所对应的预测服务质量参数，最终可以将预测服务质量参数发送至应用程序客户端。由此可见，分析预测功能组件可以响应运行在该终端设备上的应用程序客户端发送的参数预测请求，为该应用程序客户端预测相应的服务质量参数，以使后续该应用程序客户端可以基于预测服务质量参数进行适应性调整，从而可以在服务质量机制中拓展应用程序客户端感知预测服务质量参数的能力。
附图说明
图1是本申请实施例提供的一种系统架构示意图；
图2是本申请实施例提供的一种数据处理的场景示意图；
图3是本申请实施例提供的一种数据处理方法的流程示意图；
图4是本申请实施例提供的一种数据处理过程的交互示意图；
图5是本申请实施例提供的一种数据处理方法的流程示意图；
图6是本申请实施例提供的一种参数预测通知过程的交互示意图；
图7是本申请实施例提供的一种数据处理方法的流程示意图；
图8是本申请实施例提供的一种数据处理方法的流程示意图；
图9是本申请实施例提供的一种数据处理方法的流程示意图；
图10是本申请实施例提供的一种数据处理装置的结构示意图；
图11是本申请实施例提供的一种数据处理装置的结构示意图；
图12是本申请实施例提供的一种网元装置的结构示意图；
图13是本申请实施例提供的一种计算机设备的结构示意图；
图14是本申请实施例提供的一种网元设备的结构示意图；
图15是本申请实施例提供的一种数据处理系统的结构示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
本申请实施例的技术方案可以应用于各种通信系统，例如：全球移动通信系统(Global System for Mobile communication，GSM)、码分多址(Code Division Multiple Access，CDMA)系统、宽带码分多址(Wideband Code Division Multiple Access，WCDMA)系统、通用分组无线业务(General Packet Radio Service，GPRS)、长期演进(Long Term Evolution，LTE)系统、LTE频分双工(Frequency Division Duplex，FDD)系统、LTE时分双工(Time Division Duplex，TDD)、通用移动通信系统(Universal Mobile Telecommunications System，UMTS)、全球互联微波接入(Worldwide Interoperability for Microwave Access，WiMAX)通信系统、未来的第五代(5th Generation，5G)移动通信系统或后续演进的移动通信系统等。
请参见图1，是本申请实施例提供的一种系统架构示意图。如图1所示，该系统架构可以应用于支持上行业务(例如流媒体业务)的业务场景中，如视频会议、视频点播、远程教育等多媒体实时业务，这些不同业务对应的应用需要有不同的QoS(Quality of Service)要求，从而导致各种应用对服务质量的需求在迅速增长。其中，QoS是网络与用户之间以及网络上互相通信的用户之间关于信息传输与共享的质的约定，例如，传输延迟时间、数据传输的保障比特率等，是用来解决网络延迟和阻塞等问题的一种技术。可以理解，QoS对某些关键应用和多媒体应用十分必要，当网络过载或拥塞时，QoS能确保重要业务流(例如直播过程中产生的音视频流)不受延迟或丢弃，同时保证网络的高效运行。
可以理解，随着网络多媒体技术的飞速发展，各类应用层出不穷，尤其对于具有高速率、低时延和大连接特点的第五代移动通信技术(简称5G)，QoS与5G结合使用可以有益于有效地分配网络带宽，且更加合理地利用网络资源。
如图1所示，该系统架构可以包括业务服务器100以及终端集群，终端集群可以包括：终端设备200a、终端设备200b、终端设备200c、…、终端设备200n，其中，终端集群之间可以存在通信连接，例如终端设备200a与终端设备200b之间存在通信连接，终端设备200a与终端设备200c之间存在通信连接。同时，终端集群中的任一终端设备可以与业务服务器100存在通信连接，例如终端设备200a与业务服务器100之间存在通信连接，其中，上述通信连接不限定连接方式，例如，可以通过4G无线接入方式，也可以通过5G无线接入方式等，本申请对此不做限制。
应该理解，如图1所示的终端集群中的每个终端设备均可以安装有应用程序客户端，当该应用程序客户端运行于各终端设备中时，可以分别与上述图1所示的业务服务器100之间进行数据交互，使得业务服务器100可以接收来自于每个终端设备的业务数据。其中，该应用程序客户端可以为直播应用、社交应用、即时通信应用、游戏应用、短视频应用、视频应用、音乐应用、购物应用、小说应用、支付应用、浏览器等具有显示文字、图像、音频以及视频等数据信息功能的应用程序客户端。其中，该应用程序客户端可以为独立的客户端，也可以为集成在某客户端(例如即时通信客户端、社交客户端、视频客户端等)中的嵌入式子客户端，在此不做限定。
以直播应用为例，业务服务器100可以为包括直播应用对应的后台服务器、数据处理服务器等多个服务器的集合，因此，每个终端设备均可以通过该直播应用对应的应用程序客户端与业务服务器100进行数据传输，如主播用户可以通过其持有的终端设备(例如，终端设备200a)上所安装的直播应用对应的应用程序客户端进行直播，其它终端设备(例如，终端设备200b、终端设备200c以及终端设备200n等)则可以通过业务服务器100参与到该场直播中。其中，直播是指通过音视频采集设备采集主播方数据，经过一系列处理，如通过视频编码压缩成可观看可传播的视频流(或者，通过音频编码压缩成可收听可传播的音频流)，输出至观看用户端的技术。
需要说明的是，在移动通信中，如图1所示的系统架构还可以包括无线接入网(Radio Access Network，RAN)、承载网(即传输网)以及核心网，接入网中可以部署多个接入网网元(也可称为接入网设备，如5G基站gNB)，主要负责终端设备在无线侧的接入与管理；承载网可以由一系列运营商的交换和路由设备组成，主要用于传输无线接入网与核心网之间的控制信令与用户数据；核心网则可以部署一系列核心网网元(也可称为核心网设备，“网元”也可称为“网络功能”)，这些核心网网元协同对终端设备进行鉴权、计费和移动性管理等，可选的，核心网网元可以包括移动管理实体(Mobility Management Entity，MME)、广播多播服务中心(Broadcast Multicast Service Center，BMSC)等，或者也可以包括5G系统中的相应功能实体，例如会话管理网元、移动性管理网元、策略控制网元等。其中，核心网网元与接入网网元可以是独立的不同的物理设备，也可以是将核心网网元的功能与接入网网元的功能集成在同一个物理设备上，还可以是一个物理设备上集成了部分核心网网元的功能和部分接入网网元的功能。终端设备可以是固定位置的，也可以是可移动的。
为便于后续实施例的理解和说明，这里先对本申请实施例主要涉及到的网元或设备进行简要介绍，具体如下：
(1)SMF(Session Management Function，会话管理功能)：主要负责会话建立、修改和释放，用户面选择与控制，UE IP(UE，User Equipment，即终端设备或用户设备；IP，Internet Protocol，即互联网协议)地址分配等。在本申请实施例中，SMF也可以称为会话管理网元。
(2)UPF(User Plane Function，用户平面功能)：主要负责移动核心网用户面的数据路由和转发，并与外部数据网络(Data Network，比如运营商业务、互联网或者第三方业务等)互连。UPF是5G核心网中处理用户面数据的主要模块。在本申请实施例中，UPF也可 以称为用户面网元。
(3)PCF(Policy Control Function，策略控制功能)：主要负责使用统一的策略框架来管理网络行为，并协同UDR(Unified Data Repository，统一数据存储库)中的用户信息，来执行相关的策略。在本申请实施例中，PCF也可以称为策略控制网元。
(4)接入网网元是终端设备通过无线方式接入到移动通信系统中的接入设备，可以是基站NodeB、演进型基站eNodeB、5G移动通信系统中的基站(gNodeB，gNB)、未来移动通信系统中的基站或无线保真(Wireless Fidelity，WiFi)系统中的接入节点等，还可以是云无线接入网络(Cloud Radio Access Network，CRAN)场景下的无线控制器，或者可以为中继站、接入点、车载设备、可穿戴设备以及未来5G网络中的网络设备或者未来演进的PLMN网络(Public Land Mobile Network，公用陆地移动通信网络)中的网络设备等，本申请实施例对接入网网元所采用的具体技术和具体设备形态不做限定。
(5)终端设备：可以指用户设备(User Equipment，UE)、接入终端、V2X(Vehicle to X)通信中的终端、用户单元、用户站、移动站、移动台、远方站、远程终端、移动设备、用户终端、无线通信设备、用户代理或用户装置。终端设备还可以是蜂窝电话、无绳电话、会话启动协议(Session Initiation Protocol，SIP)电话、无线本地环路(Wireless Local Loop，WLL)站、个人数字处理(Personal Digital Assistant，PDA)、具有无线通信功能的手持设备、计算设备或连接到无线调制解调器的其它处理设备、车载设备、可穿戴设备，未来5G网络中的终端设备或者未来演进的公用陆地移动通信网络(PLMN)中的终端设备等，本申请实施例对此不做限定。终端设备还可以包括V2X设备，例如为车辆或车辆中的车载单元(On Board Unit，OBU)。
需要说明的是，上述会话管理网元、用户面网元、策略控制网元以及接入网网元仅是一个名字，名字对设备本身不构成限定。例如，会话管理网元也可以称作会话管理功能实体，或称为会话管理功能等，本申请对设备名称不做限定。在5G网络以及未来其它网络中，本申请实施例提及的网元也可以是其它的名字，对此不做限定。
可选的，会话管理网元、用户面网元、策略控制网元可以分别是单独的网元，也可以是由多个网元共同实现，还可以作为一个网元内的功能模块，本申请实施例对此不做限定。
可选的，图1所示的系统架构可以应用于5G网络以及未来其它可能的网络，本申请实施例对此不做具体限定。
为便于理解，以终端设备200a和终端设备200b为例进行说明。在直播的业务场景中，假设主播用户通过终端设备200a进行直播，则终端设备200a可以实时采集该主播用户的原始音视频数据，并对原始音视频数据进行前处理(例如图像美化、风格化)，进而可以对前处理后的音视频数据进行编码处理(即数字化)以及加工(如音视频混合、打包封装等)，从而得到可用的音视频流(即音频流和视频流的统称)。其中，编码通过压缩音视频数据来减少数据量，可方便音视频数据的推流、拉流和存储，从而可以大大提高存储传输效率。常用的编码方式有CBR(Constant Bit Rate，恒定比特率，一种固定采样率的压缩方式)、VBR(Variable Bit Rate，可变比特率)，对于视频数据，常用的编码标准包括H.265(H.265-HEVC(High Efficiency Video Coding)，国际电联于2013年通过的高效视频编码标 准)、H.264(由国际电联和国际标准化组织共同提出的高度压缩数字视频编解码器标准)、MPEG-4(Moving Picture Experts Group 4，动态图象专家组于1999年推出的适用于低传输速率应用的方案)等，可封装为MKV(Matroska Video File)、AVI(Audio Video Interleaved)、MP4(MPEG-4的一个缩写)等文件格式；对于音频数据，常用的编码标准包括G.711(是国际电信联盟定制出来的一套语音压缩标准)、AAC(Advanced Audio Coding，于1997年推出的基于MPEG-2的音频编码技术)、Opus(一个有损声音编码的格式)等，可封装为MP3(Moving Picture Experts Group Audio Layer III)、OGG(OGGVobis(oggVorbis))、AAC等文件格式。本申请对客户端的编码方式不进行限制。
进一步，终端设备200a可以将编码完成后的音视频流发送至业务服务器100，例如，在5G网络中，业务服务器100部署在移动通信网外部的数据网络(Data Network，DN)中，如Internet(因特网)、WAP(Wireless Application Protocol，无线应用协议)、企业内部网等，则终端设备200a可以将音视频流发送至基站，再由基站将该音视频流转发至5G核心网(5G Core，可简称为5GC)中的核心网网元UPF(即用户面网元)，通过核心网网元UPF转发后，可将该音视频流发送到外部数据网络中的业务服务器100上，而5G核心网中的其它核心网网元主要是控制面的网元，负责处理信令，实现移动性管理、会话管理、策略控制等，从而控制整个流程。随后，业务服务器100可以将该音视频流再通过核心网网元UPF以及基站下发至虚拟直播间中的其它终端设备，例如可以下发至终端设备200b，则终端设备200b可以通过相关硬件或软件对接收到的音视频流进行解码，得到可以直接显示的图像画面或声音，进而可以播放相应的图像画面或声音。其中，终端设备200a与业务服务器100之间、业务服务器100与终端设备200b之间均可以通过RTMP(Real Time Messaging Protocol，实时消息传送协议)、RTSP(Real Time Streaming Protocol，实时流传输协议)、RTP(Real-time Transport Protocol，实时传输协议)或RTCP(Real-time Transport Control Protocol，实时传输控制协议)等传输协议进行音视频流的传输。
可以理解的是，本申请实施例中的业务服务器可以是独立的物理服务器，也可以是多个物理服务器构成的服务器集群或者分布式系统，还可以是提供云数据库、云服务、云计算、云函数、云存储、网络服务、云通信、中间件服务、域名服务、安全服务、CDN、以及大数据和人工智能平台等基础云计算服务的云服务器。终端设备可以是智能手机、平板电脑、笔记本电脑、台式计算机、掌上电脑、移动互联网设备(mobile internet device,MID)、可穿戴设备(例如智能手表、智能手环等)、智能电脑、智能车载设备等可以运行上述应用程序客户端(例如直播应用的应用程序客户端)的智能终端。
需要说明的是，为了进一步提高网络业务的服务质量，可以为上述图1所述的系统架构配置QoS能力。可以理解，QoS流是PDU会话(即协议数据单元会话)中QoS区分的最细粒度。当该系统架构应用于5G网络时，对于同一个QoS流控制的业务流，会使用相同的流量转发处理(如调度、准入门限等)。对于一个终端设备，可以与5G网络建立一个或者多个PDU会话；每个PDU会话中可以建立一个或者多个QoS流。每个QoS流由一个QoS流标识(QoS flow identifier，QFI)识别，一个QFI在一个PDU会话中唯一标识一个QoS流。此外，每个QoS流对应一个数据无线承载(Data Radio Bearer，DRB)，一个DRB可以对应一个或 多个QoS流。其中，一个QoS流为GBR QoS流还是Non-GBR QoS流，由对应的QoS配置文件(QoS Profile)确定。
5G核心网支持终端设备和数据网络间的PDU连接业务，PDU连接业务通过PDU会话的形式来体现，一个PDU会话是指一个终端设备与数据网络之间进行通讯的数据通路。假设一个终端设备(例如终端设备200a)希望获得某个应用服务(例如直播服务)，则该终端设备可以向5G核心网中的核心网网元SMF(即会话管理网元)发起一个PDU会话建立请求，在PDU会话建立过程中，核心网网元SMF可以根据QoS和服务要求，将PCC规则(即策略控制和计费规则)绑定到QoS流，核心网网元SMF可以为新的QoS流分配QFI，并从绑定到该QoS流的PCC规则和核心网网元PCF(即策略控制网元)提供的其它信息中导出其QoS配置文件、相应的UPF指令以及QoS规则，随后，核心网网元SMF可以将QoS配置文件发送至无线接入网(R)AN(即接入网网元)，将相应的UPF指令发送至核心网网元UPF，将QoS规则发送至终端设备。此外，核心网网元SMF也可以同时将流级别的QoS参数(QoS Flow level QoS parameter)发送给终端设备，这些QoS参数与对应的QoS规则相关联。进一步，终端设备接收到该QoS规则和QoS参数后，可以基于QoS规则对上行的业务流(也可称为上行用户平面流量)进行分类和标记，例如，可以根据QoS规则将业务流(如音视频流)映射到QoS流，进而可以将QoS流绑定到AN资源(AN resources，如3GPP无线接入网场景下的数据无线承载DRB)。其中，一个QoS流可以关联一个或多个QoS规则。
可以理解，当网络发生拥塞的时候，所有的业务流都有可能被丢弃，而配置QoS后，可以对不同的业务流提供不同的服务质量，即不同的QoS流对应不同的QoS转发待遇，例如，对实时性强且重要的业务数据包优先处理；对于实时性不强的普通业务数据包，则提供较低的处理优先级，网络拥塞时甚至丢弃。也就是说，支持QoS功能的网络，能够提供传输品质服务，即针对某种类别的业务流，可以为它赋予某个级别的传输优先级，来标识它的相对重要性，并使用网络所提供的各种优先级转发策略、拥塞避免等机制为这些业务流提供特殊的传输服务。上述可知，配置了QoS的网络环境，可以增加网络性能的可预知性，并能够有效地分配网络带宽，更加合理地利用网络资源。
需要说明的是，针对启用了通知控制的GBR QoS流，本申请实施例还可以提供替代QoS配置文件，具体而言，如果相应的PCC规则包含相关信息，则除了QoS配置文件外，核心网网元SMF还应向无线接入网(R)AN提供替代QoS配置文件的优先级列表。如果核心网网元SMF向无线接入网(R)AN提供了一个新的替代QoS配置文件的优先级列表(若相应的PCC规则信息发生变化)，则无线接入网(R)AN将用其替换任何先前存储的列表。其中，替代QoS配置文件可以表示业务流能够适应的QoS参数的组合，该QoS参数的组合可以包括保证流比特率(Guaranteed Flow Bit Rate，GFBR)、误包率(Packet Error Rate，PER)以及包延迟预算(Packet Delay Budget，PDB)。此外，当无线接入网(R)AN向核心网网元SMF发送不满足QoS配置文件的通知时，如果当前满足的参数值与替代QoS配置文件匹配，则无线接入网(R)AN还应包括替代QoS配置文件的引用，用以指示无线接入网(R)AN当前满足的QoS，进而可以发送相关通知给核心网网元SMF，核心网网元SMF则会进一步更新相应的QoS参数并发送给终端设备。其中，QoS参数会影响无线接入网(R)AN对不同等级用户、不同等级业 务的调度算法和策略，例如，基站可以基于上述的QoS参数以及其它核心网参数，指导无线侧的资源分配。
此外，本申请实施例提供了一种业务传输优化方法，当PDU会话建立时，终端设备上该PDU会话对应的应用程序客户端(例如直播应用)可以生成参数预测请求，进而可以将该参数预测请求发送至分析预测功能组件，其中，该应用程序客户端运行于终端设备中，且分析预测功能组件也集成在该终端设备中。进一步，分析预测功能组件可以基于该参数预测请求，为该应用程序客户端预测与其业务数据包相关联的QoS流所对应的预测服务质量参数，进而可以将该预测服务质量参数发送至该应用程序客户端。可以理解，终端设备上的分析预测功能组件可以根据过往的QoS参数信息(即历史参数信息)，预测某个QoS流的参数变化，例如，服务质量流X1在地点X2处被降级为较低的GFBR值，如果在历史上该模式重复出现，则分析预测功能组件可以预测服务质量流X1的QoS在地点X2处可能会降低GFBR，因此分析预测功能组件可以将预测得到的GFBR(即预测服务质量参数)发送给服务质量流X1对应的应用程序客户端X3。由此可知，终端设备上的应用程序客户端可以感知预测服务质量参数及其变化，因此可以使用预测服务质量参数来执行一些相关的处理工作，例如，可以基于预测服务质量参数进行适应性调整，从而可以在QoS机制中拓展应用程序客户端获取并使用预测服务质量参数的能力。需要说明的是，本申请实施例提供的方法对上行流媒体业务十分有效，例如，应用程序客户端可以基于预测服务质量参数进行编码算法的调整，从而可以提升传输效率，典型场景如体育馆比赛直播、演唱会直播、无人机图像回传、道路摄像机视频回传等。
为便于理解，请一并参见图2，图2是本申请实施例提供的一种数据处理的场景示意图。该数据处理场景的实现过程主要在终端设备(即UE)内部进行。本申请实施例中的终端设备A可以为任意一个终端设备，例如，可以为上述图1所示的终端设备200a。如图2所示，终端设备A上可以安装并运行一个或多个应用程序客户端，假设一共有N个应用程序客户端，其中，N为正整数，分别为应用程序客户端A1、应用程序客户端A2、…、应用程序客户端AN，每个应用程序客户端可以对应于一种或多种业务，当用户存在某种业务需求时，可以通过在终端设备A上选择运行某个应用程序客户端来获取相应的应用服务。其中，当终端设备A建立PDU会话后，应用程序客户端可以与相应的服务器端进行数据传输，在这个过程中，应用程序客户端可能会向服务器端传输一些上行的信息，例如摄像头、麦克风等设备采集并处理后得到的音视频流，即上行的业务流，为了提高网络业务的服务质量，本申请实施例可以基于QoS流为这些业务流提供不同的转发处理。
需要说明的是，在PDU会话建立过程中，会话管理网元(即SMF)可以根据本地策略或策略控制网元发送的PCC规则确定建立服务质量流，则会话管理网元可以通过接入和移动性管理网元(Access and Mobility Management Function，简称AMF，也可称为接入和移动性管理功能)和无线接入网(RAN，即接入网网元)向终端设备A发送服务质量规则和对应的流级别的服务质量参数组成的服务质量参数集，其中，一个服务质量规则中可以包括相关服务质量流的QFI、一个包过滤器集(Packet Filter Set)以及一个优先级值，需要说明的是，一个包过滤器集可以包含多个包过滤器，每个包过滤器可以是上行或下行或双向 的。例如，如图2所示，终端设备A可以获取到服务质量规则R1、服务质量规则R2、服务质量规则R3等多个服务质量规则，以及与这些服务质量规则相关的服务质量参数组成的服务质量参数集；会话管理网元可以通过接入和移动性管理网元向无线接入网发送服务质量流相关的QoS配置文件；向用户面网元(即UPF)发送业务数据流(Service Data Flow，SDF)信息，该SDF信息中包括QoS控制信息。进而终端设备A、无线接入网和用户面网元之间可以建立起服务质量流，例如，服务质量流F1、服务质量流F2、服务质量流F3等，而无线接入网可以根据QoS配置文件建立空口的数据无线承载(即DRB，属于AN资源)，并存储服务质量流与数据无线承载的绑定关系，例如，服务质量流F1以及服务质量流F2与数据无线承载D1绑定，服务质量流F3与数据无线承载D2绑定。需要说明的是，本申请实施例对于服务质量流、服务质量规则以及数据无线承载的数量不做具体限定。
进一步，针对上行链路(即UL)，当终端设备A确定发送上行的业务数据包(UL packet)时，如图2所示，假设在PDU会话中产生了业务流C，其中包括了可能来自于终端设备A上的任意一个或多个应用程序客户端的业务数据包，例如，应用程序客户端A1，则对于IP类型(Type IP)或者以太网类型(Type Ethernet)的PDU会话，终端设备A可以根据服务质量规则的优先级值，按照一定的优先级顺序对服务质量规则中的包过滤器集中的上行包过滤器(UL Packet Filter)来评估业务流C中的业务数据包，直到找到匹配的服务质量规则；若没有找到匹配的服务质量规则，则终端设备A将丢弃该业务数据包。而对于非结构化类型(Type Unstructured)的PDU会话，默认服务质量规则不包含包过滤器集，将允许所有的上行业务数据包。需要说明的是，对于非结构化类型的PDU会话，只有默认的服务质量规则存在。进而终端设备A可以使用匹配到的服务质量规则中的QoS流标识(即QFI)，将业务流C中的业务数据包映射到相应的服务质量流，即使用QoS流标识对业务数据包进行标记。例如，如图2所示，根据服务质量规则R1可以将业务流C中的部分业务数据包映射到服务质量流F1，根据服务质量规则R2可以将业务流C中的部分业务数据包映射到服务质量流F2，根据服务质量规则R3可以将业务流C中的另外一部分业务数据包映射到服务质量流F3。
进一步，可以根据这些服务质量流与数据无线承载的绑定关系，将上述业务数据包放在对应的数据无线承载上传输，例如，服务质量流F1中的业务数据包以及服务质量流F2中的业务数据包可以在数据无线承载D1上传输，服务质量流F3中的业务数据包可以在数据无线承载D2上传输。当无线接入网接收到数据无线承载D1以及无线承载D2上传输过来的业务数据包时，可以通过N3接口向用户面网元传输业务数据包，用户面网元接收到业务数据包后，可以基于QoS流标识验证这些业务数据包是否使用正确的服务质量流传输，并根据会话管理网元下发的业务检测、转发、上报和计费规则等，对业务数据包进行相应的处理。
本申请实施例对于下行链路(即DL)的处理流程不进行展开。
此外，如图2所示，终端设备A上还集成有分析预测功能组件B，分析预测功能组件B可以为终端设备A上的应用程序客户端预测相应的服务质量参数，在一种可选的实施方式中，该分析预测功能组件B可以提供分析预测接口供应用程序客户端调用。当PDU会话建立时或PDU会话建立后，终端设备A上对应于该PDU会话的应用程序客户端可以生成并发送参数预测请求给分析预测功能组件B，分析预测功能组件B接收到该参数预测请求后，可以 响应该参数预测请求，即基于该参数预测请求为该应用程序客户端预测与其业务数据包相关联的目标服务质量流所对应的预测服务质量参数，进而可以将该预测服务质量参数返回给该应用程序客户端。以应用程序客户端A1为例，假设应用程序客户端A1的业务数据包经过前述过程映射到了服务质量流F1，则应用程序客户端A1可以通过分析预测接口发起参数预测请求，进而分析预测功能组件B可以判断出应用程序客户端A1的业务数据包属于服务质量流F1，随后可以将针对服务质量流F1所预测得到的服务质量参数E(即预测服务质量参数)通过分析预测接口发送给应用程序客户端A1。可以理解，在PDU会话过程中，当分析预测功能组件B预测到服务质量流F1的实际服务质量参数可能发生变化(即具有变化趋势)时，可以通知应用程序客户端A1，例如，可以根据预测到的变化趋势生成参数变化通知消息，并将该参数变化通知消息发送至应用程序客户端A1，随后应用程序客户端A1可以重新发起参数预测请求，或者，分析预测功能组件B可以将分析预测结果(即预测服务质量参数)添加到参数变化通知消息后发送给应用程序客户端A1。可以理解的是，上述分析预测功能组件B提供的分析预测接口是终端设备A内部的接口，预测相应的服务质量参数的过程是在终端设备A内部实现。
需要说明的是，应用程序客户端获取到相应的预测服务质量参数后，可以使用该预测服务质量参数，例如，若应用程序客户端A1为流媒体业务(如直播业务)相关的客户端，则当接收到服务质量参数E时，应用程序客户端A1可以进行适应性调整，例如可以基于服务质量参数E来调整其采用的编码算法(如调整编码率、压缩率等，需要综合考虑)，从而得到优化业务数据包，随后终端设备A仍然可以通过前述过程发送上行的优化业务数据包，因此，可以达到节省传输带宽、提升传输效率的目的。可以理解，应用程序客户端还可以使用预测服务质量参数进行其它的处理，如调整其流媒体业务的其它发送参数，具体如何使用是应用程序客户端内部的实现，本申请对此不做限定。
请参见图3，是本申请实施例提供的一种数据处理方法的流程示意图。该数据处理方法可以由终端设备执行。本申请实施例提供的方法可以支持终端设备中的分析预测功能组件根据服务质量参数(即QoS参数)的历史参数信息，为该终端设备上的应用程序客户端预测对应的QoS流的参数变化。如图3所示，该数据处理方法至少可以包括以下S101-S102：
S101，应用程序客户端生成参数预测请求，将参数预测请求发送至分析预测功能组件；
具体的，为了给应用程序客户端提供预测相应的服务质量参数的功能(即分析预测功能)，在终端设备建立协议数据单元会话(即PDU会话)时或者建立协议数据单元会话后，该协议数据单元会话对应的应用程序客户端可以生成并发送参数预测请求给终端设备上的分析预测功能组件(也可称为分析预测功能模块)，进而分析预测功能组件可以接收该参数预测请求。其中，该参数预测请求用于请求为该应用程序客户端预测其业务流对应的服务质量流(即QoS流)或者对应的网络切片内的服务质量流的服务质量参数(即预测服务质量参数)。该应用程序客户端运行在终端设备上，可以为支持上行业务(例如传输文字、图像、音频或者视频等数据到服务器端)的客户端。
在一种实施方式中，终端设备上的分析预测功能组件可以提供API接口(Application Programming Interface，即应用程序接口)供应用程序客户端调用，在本申请实施例中，该 API接口可以称为分析预测接口，或者也可以称为分析预测功能接口，本申请对该接口的具体名称不做限定，应用程序客户端可以通过调用分析预测接口来使用分析预测功能组件所提供的预测相关的服务质量参数的功能，也就是说，应用程序客户端可以将参数预测请求发送至该分析预测接口，进而分析预测功能组件可以通过该分析预测接口获取该参数预测请求。
S102，分析预测功能组件基于参数预测请求，为应用程序客户端预测服务质量流所对应的预测服务质量参数，将预测服务质量参数发送至应用程序客户端；服务质量流与应用程序客户端所提供的业务数据包相关联。
具体的，终端设备的分析预测功能组件可以根据参数预测请求为应用程序客户端预测服务质量流对应的预测服务质量参数。其中，预测服务质量参数是由分析预测功能组件所生成的。在一种实施方式中，终端设备可以提供的预测服务质量参数包括以下QoS参数中的一个或多个：保证流比特率(GFBR)、误包率(PER)、包延迟预算(PDB)。其中，保证流比特率表示由网络保证在平均时间窗口上向服务质量流提供的最低比特率；误包率表示非拥塞相关数据包丢失率的上限；包延迟预算表征业务数据包在终端设备和用户平面网元上的终止点N6接口之间的传输时延的上限。
需要说明的是，上述服务质量流与应用程序客户端所提供的业务数据包相关联，也就是说，在建立协议数据单元会话时，会话管理网元可以向终端设备下发服务质量规则以及服务质量参数集，其中，服务质量规则可以用于对上行的业务流进行分类和标记，服务质量参数集中的服务质量参数与服务质量规则相关联。进一步，终端设备可以基于接收到的服务质量规则，将应用程序客户端所发送的业务数据包映射至相应的服务质量流，其中，与该服务质量流相关联的目标服务质量参数属于该服务质量参数集。可以理解，由于映射到同一服务质量流的业务数据包会被标记相同的服务质量流标识，因此分析预测功能组件可以通过服务质量流标识判断应用程序客户端的业务数据包属于哪个服务质量流。
需要说明的是，在本申请实施例中，除了保证流比特率、误包率、包延迟预算以外，服务质量参数集还可以包括但不限于以下QoS参数：5G QoS标识(5G QoS identifier，5QI)、分配和预留优先级(Allocation and Retention Priority，ARP)、最大流比特率(MFBR)、反射QoS属性(Reflective QoS Attribute，RQA)、服务质量通知控制(QoS Notification Control，QNC)、优先级别(Priority Level)。
在一种实施方式中，分析预测功能组件可以分析预测该终端设备上的业务流对应的QoS流的QoS参数变化情况。具体的，终端设备上的分析预测功能组件通过分析预测接口接收到参数预测请求后，可以根据参数预测请求获取与该应用程序客户端相关联的服务质量流标识(即QFI)，并识别出该服务质量流标识所对应的服务质量流，进一步，分析预测功能组件可以基于该目标服务质量参数对应的历史参数信息，预测该服务质量流对应的预测服务质量参数，具体的，可以将该目标服务质量参数对应的历史参数信息输入预先训练好的参数预测模型，通过该参数预测模型可以提取历史参数信息对应的参数变化特征，进而可以基于该参数变化特征对该目标服务质量参数进行调整，从而得到该服务质量流对应的预测服务质量参数。
其中，历史参数信息可以包括统计时间段内应用程序客户端上的业务流对应的服务质量流的服务质量参数变化情况，则参数变化特征可以表示可能导致该变化的影响因素，例如环境因素(时间、地点等)、接入的数据网络或网络切片等。例如，在统计时间段内，多次重复出现某个GBR QoS流在某个时间段(可称为目标时间段，例如上午8点-10点)内被降级为较低的GFBR值，则分析预测功能组件可以通过参数预测模型提取出相应的参数变化特征W1(与目标时间段相关)，进而可以基于参数变化特征W1预测出在该目标时间段可能会降低该QoS流的GFBR值，则可以将该QoS流当前的GFBR值调整到一个较低的值，然后将调整后得到的GFBR确定为预测服务质量参数。同理，该QoS流在某个地点(可称为目标地点，例如地点L)时对应的PDB下降，如果这种情况在统计时间段内重复出现，则分析预测功能组件可以通过参数预测模型提取出相应的参数变化特征W2(与目标地点相关)，进而可以基于参数变化特征W2预测出在该目标地点可能会降低该QoS流的PDB值，则可以将该QoS流当前的PDB值调整到一个较低的值，然后将调整后得到的PDB确定为预测服务质量参数。最终，分析预测功能组件可以通过分析预测接口将预测生成的预测服务质量参数发送至应用程序客户端，因此应用程序客户端可以调整其业务相关的发送参数(如编码率、压缩率等)。
可选的，分析预测功能组件也可以分析预测该终端设备上的业务流所属的网络切片的整体性能变化情况。具体的，终端设备上的分析预测功能组件接收到参数预测请求后，可以根据参数预测请求获取与该应用程序客户端相关联的网络切片选择辅助信息(即S-NSSAI，Single Network Slice Selection ASSistance Information)，并识别出该网络切片选择辅助信息所对应的网络切片，进一步，可以基于上述服务质量参数集中与该网络切片相关联的服务质量参数对应的历史参数信息，预测服务质量流对应的预测服务质量参数，其中，该网络切片相关联的服务质量参数包括该目标服务质量参数，也就是说，该应用程序客户端运行在该网络切片上。具体的，同样可以将该网络切片相关联的服务质量参数对应的历史参数信息输入预先训练好的参数预测模型，通过该参数预测模型可以提取历史参数信息对应的参数变化特征，进而可以基于该参数变化特征对该网络切片相关联的服务质量参数进行调整，从而得到该服务质量流(以及该网络切片上的其它QoS流)对应的预测服务质量参数。其中，历史参数信息可以包括统计时间段内应用程序客户端上的业务流所属的网络切片的整体性能变化情况，则参数变化特征可以表示可能导致该变化的影响因素，例如环境因素(时间、地点等)、接入的数据网络或网络切片等。例如，在统计时间段内，某个网络切片(如网络切片S)上的业务流的平均速率在某个时间段或某个地点会比较高，或者时延较低，且这种情况重复出现，则分析预测功能组件可以通过参数预测模型生成相应的分析预测结果(即预测服务质量参数)。最终，终端设备上的分析预测功能组件可以通过分析预测接口将预测生成的预测服务质量参数发送给该网络切片上运行的所有应用程序客户端(包括上述应用程序客户端)，进而这些应用程序客户端可以调整其业务相关的发送的业务数据包。可以理解，与上述基于服务质量流的参数预测方式相比，基于网络切片的参数预测方式考虑到的是更高维度的参数变化特征，可以根据实际情况选择恰当的参数预测方式，本申请对此不做限定。
其中，终端设备上的分析预测功能组件可以通过分析预测接口将预测服务质量参数发送至应用程序客户端，可选的，若该应用程序客户端为执行流媒体业务的客户端，则分析预测功能组件可以生成包含预测服务质量参数的参数预测响应消息，随后可以将该参数预测响应消息发送给应用程序客户端。应用程序客户端接收到该参数预测响应消息后，可以对该参数预测响应消息进行解析，得到预测服务质量参数，进而可以基于预测服务质量参数对当前流媒体业务中所采用的编码算法进行调整(如调整编码率、压缩率等)，从而可以基于调整后的编码算法以及在流媒体业务中产生的流媒体数据，生成优化的业务数据包，后续要上传优化的业务数据包到服务器端时，终端设备仍然可以基于服务质量规则将优化的业务数据包映射到合适的服务质量流来进行传输。其中，流媒体业务是指以流的方式传输音频、视频、文本、图像、动画等流媒体数据的业务。
由此，应用程序客户端可以根据预测服务质量参数生成优化的业务数据包，使得优化的业务数据包能够符合未来传输需求的可能性提高，提升了流媒体业务的服务质量。
可以理解，参数预测模型可以集成在分析预测功能组件中，例如可以作为分析预测功能组件中的一个功能模块，用于根据历史参数信息预测出对应的预测服务质量参数，其中，该参数预测模型可以是一个基于深度神经网络(Deep Neural Networks，简称DNN)的AI(Artificial Intelligence，人工智能)模型，可以通过对初始参数预测模型进行训练得到。在一种实施方式中，可以将对大量样本终端设备进行采集得到的样本参数信息(包括初始服务质量参数、样本环境信息以及变化服务质量参数)输入初始参数预测模型，进而可以通过初始参数预测模型中的特征提取层提取出初始服务质量参数以及样本环境信息对应的样本参数变化特征，进一步，可以在该初始参数预测模型的输出层中，基于该样本参数变化特征生成对应的样本预测服务质量参数，进而可以输出样本预测服务质量参数，随后可以根据样本预测服务质量参数以及变化服务质量参数生成损失函数，进而可以基于该损失函数对初始参数预测模型的模型参数进行调整，直到模型收敛，最终可以得到训练好的参数预测模型。由此基于历史参数信息，通过参数预测模型可以准确基于历史参数信息确定出参数变化特征。
请一并参见图4，图4是本申请实施例提供的一种数据处理过程的交互示意图。如图4所示，该数据处理过程可以包括如下步骤：
S201，当终端设备建立协议数据单元会话时或者建立协议数据单元会话后，终端设备上的对应于该协议数据单元会话的应用程序客户端会发送分析预测参数请求(即参数预测请求)给分析预测功能组件(可提供分析预测功能)；
S202，分析预测功能组件通过分析预测接口接收到分析预测参数请求后，可以判断该应用程序客户端的业务数据流属于哪个QoS流或者哪个网络切片，并把该应用程序客户端的业务流对应的QoS流或者网络切片的参数预测信息(即预测服务质量参数)发送给该应用程序客户端。
此外，本申请实施例还提供了参数预测通知功能，通过参数预测通知功能可以为应用程序客户端提供预测到的参数变化信息，具体过程可以参见后续图5所对应实施例中的S304。
本申请实施例可以支持终端设备上协议数据单元会话对应的应用程序客户端生成参数 预测请求，并将参数预测请求发送至该终端设备中的分析预测功能组件，进而分析预测功能组件可以基于该参数预测请求为应用程序客户端预测服务质量流所对应的预测服务质量参数，最终可以将预测服务质量参数发送至应用程序客户端。由此可见，当终端设备建立协议数据单元会话时或者建立协议数据单元会话后，分析预测功能组件就可以响应运行在该终端设备上的应用程序客户端发送的参数预测请求，为该应用程序客户端预测相应的服务质量参数，以使后续该应用程序客户端可以基于预测服务质量参数进行适应性调整，从而可以在服务质量机制中拓展应用程序客户端获取并使用预测服务质量参数的能力，且提升传输效率。
进一步地，请一并参见图5，图5是本申请实施例提供的一种数据处理方法的流程示意图。该数据处理方法可以由终端设备执行，该终端设备包括应用程序客户端以及分析预测功能组件。如图5所示，该数据处理方法至少可以包括以下步骤：
S301，终端设备获取移动核心网网元下发的第一功能指令；
具体的，终端设备可以获取移动核心网网元下发的第一功能指令，其中，第一功能指令用于指示终端设备是否向应用程序客户端开放分析预测功能组件的分析预测功能，其中，可选的，移动核心网网元可以是会话管理网元(或称为会话管理功能)，也可以是其它网元，本申请对此不做限定。
可以理解，终端设备是否向应用程序客户端开放分析预测功能组件的分析预测功能是由移动核心网网元指示决定的，即会话管理网元在向终端设备下发服务质量规则以及对应的服务质量参数集时，移动核心网网元会进一步指示是否允许开放相关QoS流或网络切片的分析预测接口供应用程序客户端调用。
S302，分析预测功能组件获取协议数据单元会话对应的应用程序客户端所发送的参数预测请求；
该步骤的具体过程可以参见上述图3所对应实施例中的S101，这里不再进行赘述。
S303，若第一功能指令为功能开放指令，则分析预测功能组件基于参数预测请求为应用程序客户端预测服务质量流所对应的预测服务质量参数，将预测服务质量参数发送至应用程序客户端；
具体的，当第一功能指令为功能开放指令，即移动核心网网元指示可以开放分析预测接口时，分析预测功能组件可以基于参数预测请求为该应用程序客户端预测服务质量流所对应的预测服务质量参数，并将预测服务质量参数发送至应用程序客户端，其中，预测服务质量流所对应的预测服务质量参数并将其发送至应用程序客户端的具体过程可以参见上述图3所对应实施例中的S102，这里不再进行赘述。其中，功能开放指令可以指示终端设备向应用程序客户端开放分析预测功能组件的分析预测功能。
S304，应用程序客户端向分析预测功能组件签约参数预测通知功能，当分析预测功能组件预测到目标服务质量参数具有变化趋势或者预测服务质量参数超过门限值时，基于参数预测通知功能，通知应用程序客户端；
具体的，终端设备上的应用程序客户端可以通过分析预测接口向分析预测功能组件签约参数预测通知功能，签约成功后，当分析预测功能组件预测到目标服务质量参数具有变 化趋势或者预测服务质量参数超过门限值时，可以基于参数预测通知功能生成参数变化通知消息，进而可以通过分析预测接口将该参数变化通知消息发送至应用程序客户端，随后应用程序客户端可以基于该参数变化通知消息重新向分析预测功能组件发起参数预测请求，进而可以经过类似上述图3所对应实施例中描述的过程，通过分析预测接口将重新预测得到的服务质量参数发送给应用程序客户端。应用程序客户端也可以在签约请求中进一步包含通知的最大次数，预测服务质量参数对应的门限值等参数信息。其中，门限值可以根据业务需要进行设置，本申请对门限值的具体大小不进行限定。通过设置门限值，分析预测功能组件可以不需要一预测到相关变化趋势就通过参数预测通知功能进行通知，而是在预测服务质量参数超过门限值时再进行通知，这样可以降低频繁通知对应用程序客户端的干扰，减少应用程序客户端与分析预测功能组件之间的数据交互。
可选的，在协议数据单元会话建立时，可以先由应用程序客户端主动通过分析预测接口向分析预测功能组件发起参数预测请求，以获取预测服务质量参数，而在应用程序客户端向分析预测功能组件签约参数预测通知功能后，当预测到目标服务质量参数具有变化趋势或者预测服务质量参数超过门限值时，则可以基于参数预测通知功能，由分析预测功能组件主动向应用程序客户端发送预测得到的服务质量参数或者是预测服务质量参数超过门限值的通知信息(即参数变化通知消息)。
S305，若第一功能指令为功能关闭指令，则分析预测功能组件向应用程序客户端发送请求拒绝信息。该请求拒绝信息是针对前述的参数预测请求的。
具体的，当第一功能指令为功能关闭指令，即移动核心网网元指示不可以开放分析预测功能组件的分析预测功能时，分析预测功能组件可以通过分析预测接口向应用程序客户端发送请求拒绝信息。其中，功能关闭指令用于指示终端设备不向应用程序客户端开放分析预测功能组件的分析预测功能(或者说，不向应用程序客户端开放分析预测接口)。进一步，该请求拒绝信息可以包括拒绝原因标识(也可称为拒绝原因值)，其中，拒绝原因标识用于表征针对参数预测请求的拒绝原因，由网络预先定义。例如，可以用不同的数字表示不同的拒绝原因，如数字“1”表示签约不允许，数字“2”表示切片不允许，数字“3”表示数据网络名称(Data Network Name，DNN)不允许，数字“4”表示运营商不允许等等。
也就是说，如果移动核心网网元指示不可以开放分析预测功能组件的分析预测功能，则分析预测功能组件在接收到应用程序客户端发送的参数预测请求(也可称为分析预测参数请求)时，会在相应的响应消息中指示拒绝请求，并可进一步包含拒绝原因值。
通过第一功能指令的指示，使得终端设备可以准确的判断为哪些应用程序客户端开放分析预测功能，而向哪些应用程序客户端关闭该分析预测功能，提高了有效分析预测的效率。
需要说明的是，移动核心网网元指示是否允许开放分析预测接口供应用程序客户端调用时可以考虑以下功能指示信息中的一种或多种：终端设备的签约信息、协议数据单元会话发起时携带的数据网络名称(DNN)和单个网络切片选择辅助信息(S-NSSAI)、运营商自己的配置、网络的策略等，例如，可能任意一个终端设备都允许/都不允许开放分析预测接口，也可能对于指定了特定网络切片的业务，该业务可以允许开放分析预测接口，本申 请实施例对移动核心网网元具体采用何种许可策略不做限定。
在本申请实施例中，通过终端设备向移动核心网网元发送第二功能指令，可以准确通知移动核心网网元终端设备对分析预测功能的支持情况，使得移动核心网网元可以基于终端设备的支持情况，有选择的向支持服务质量接口的终端设备发送第一功能指令，降低了无效发送第一功能指令的可能(例如向不支持分析预测功能的终端设备发送)，提高了交互效率。
请一并参见图6，图6是本申请实施例提供的一种参数预测通知过程的交互示意图。如图6所示，该过程可以包括如下步骤：
S401，应用程序客户端向分析预测功能组件(或者称为UE分析预测功能模块)签约分析预测参数通知(即参数预测通知功能)；
S402，当分析预测接口得到该应用程序客户端的业务流对应的QoS流的分析预测结果(即预测服务质量参数)，或者，预测到该QoS流相关联的服务质量参数可能发生变化(即具有变化趋势)，或者，预测服务质量参数超过门限值时，分析预测功能组件可以通过分析预测接口通知该应用程序客户端。
上述可知，签约参数预测通知功能后，应用程序客户端可以不需要频繁向分析预测功能组件发送参数预测请求，而是可以在相关的服务质量参数可能发生变化时，或者预测服务质量参数超过门限值时，或者生成相应的分析预测结果时，通过分析预测接口主动通知应用程序客户端关于该服务质量参数可能发生的变化，或直接发送得到的分析预测结果，或者是预测服务质量参数超过门限值的通知信息，从而可以使应用程序客户端能够直接感知到服务质量参数可能发生的变化，并提升预测服务质量参数的获取效率。
进一步地，请一并参见图7，图7是本申请实施例提供的一种数据处理方法的流程示意图。该数据处理方法可以由终端设备执行，终端设备包括应用程序客户端和分析预测功能组件。如图7所示，该数据处理方法至少可以包括以下步骤：
S501，终端设备将第二功能指令发送至移动核心网网元；
具体的，终端设备在发起协议数据单元会话时，可以指示移动核心网网元该终端设备是否支持分析预测功能组件的分析预测功能，即向移动核心网网元发送第二功能指令。在一种实施方式中，第二功能指令可以作为N1SM container中的一个参数。当终端设备发送的第二功能指令为功能支持指令，即终端设备明确指示了支持分析预测功能组件的分析预测功能时，可以继续执行S502；反之，当终端设备发送的第二功能指令为功能不支持指令(即该终端设备指示不支持预测功能组件的分析预测功能)时，或者，终端设备没有指示支持预测功能组件的分析预测功能(即移动核心网网元会认为该终端设备不需要或不支持该分析预测功能)时，不需要执行后续步骤，该流程结束。其中，移动核心网网元可以为会话管理网元，也可以为其它网元，本申请对此不做限定。
S502，若第二功能指令为功能支持指令，则终端设备获取移动核心网网元下发的第一功能指令；
具体的，当移动核心网网元检测到第二功能指令为功能支持指令时，可以基于许可策略生成第一功能指令，并将第一功能指令发送至终端设备，进而终端设备可以接收第一功 能指令。该步骤的具体过程可以参见上述图5所对应实施例中的S301，这里不再进行赘述。
S503，分析预测功能组件获取协议数据单元会话对应的应用程序客户端所发送的参数预测请求；
该步骤的具体过程可以参见上述图3所对应实施例中的S101，这里不再进行赘述。
S504，若第一功能指令为功能开放指令，则分析预测功能组件基于参数预测请求为应用程序客户端预测服务质量流所对应的预测服务质量参数，将预测服务质量参数发送至应用程序客户端；
该步骤的具体过程可以参见上述图5所对应实施例中的S303，这里不再进行赘述。
S505，若第一功能指令为功能关闭指令，则分析预测功能组件向应用程序客户端发送请求拒绝信息；
该步骤的具体过程可以参见上述图5所对应实施例中的S305，这里不再进行赘述。
S506，应用程序客户端向分析预测功能组件签约参数预测通知功能，当分析预测功能组件预测到目标服务质量参数具有变化趋势或者预测服务质量参数超过门限值时，基于参数预测通知功能，通知应用程序客户端。
该步骤的具体过程可以参见上述图5所对应实施例中的S304，这里不再进行赘述。
在本申请实施例中，通过终端设备和移动核心网网元之间的交互，可以为运行在该终端设备上的应用程序客户端预测相关的服务质量参数，此外，当分析预测功能组件预测到目标服务质量参数具有变化趋势时，也可以为该应用程序客户端重新预测可能变化的服务质量参数，或者预测服务质量参数超过门限值时，通知该应用程序客户端，以使后续该应用程序客户端可以基于预测得到的服务质量参数进行适应性调整，从而可以在服务质量机制中拓展应用程序客户端获取并使用预测服务质量参数的能力。
请一并参见图8，图8是本申请实施例提供的一种数据处理方法的流程示意图。该数据处理方法可以由终端设备执行，终端设备包括应用程序客户端和分析预测功能组件。如图8所示，该数据处理方法至少可以包括以下步骤：
S601，应用程序客户端向分析预测功能组件签约针对协议数据单元会话的参数预测通知功能；协议数据单元会话与应用程序客户端提供的业务数据包相关联；
具体的，应用程序客户端可以通过分析预测接口向分析预测功能组件签约针对协议数据单元会话的参数预测通知功能，签约成功后，分析预测功能组件即可为该应用程序客户端提供预测服务质量参数。其中，该应用程序客户端运行在终端设备中，该协议数据单元会话与应用程序客户端提供的业务数据包相关联。
S602，分析预测功能组件基于参数预测通知功能为应用程序客户端预测服务质量流所对应的预测服务质量参数；服务质量流与业务数据包相关联；
具体的，终端设备上的分析预测功能组件可以基于参数预测通知功能为应用程序客户端预测服务质量流所对应的预测服务质量参数，其中，该服务质量流与应用程序客户端所提供的业务数据包相关联。在一种实施方式中，通过调用参数预测通知功能，分析预测功能组件可以基于与该应用程序客户端相关联的服务质量流标识，识别出该服务质量流标识对应的服务质量流，进而可以基于与该目标服务质量参数对应的历史参数信息，预测该服 务质量流对应的预测服务质量参数。可选的，通过调用参数预测通知功能，分析预测功能组件可以基于与应用程序客户端相关联的单个网络切片选择辅助信息，识别出该单个网络切片选择辅助信息对应的网络切片，进而可以基于服务质量参数集中与该网络切片相关联的服务质量参数对应的历史参数信息，预测该服务质量流对应的预测服务质量参数。具体的实现过程可以参见上述图3所对应实施例中的S102，这里不再进行赘述。
S603，当预测服务质量参数与目标服务质量参数不相同或者预测服务质量参数超过门限值时，分析预测功能组件将预测服务质量参数发送至应用程序客户端；目标服务质量参数是由会话管理网元所下发的。
具体的，终端设备上的分析预测功能组件可以将预测服务质量参数和由会话管理网元所下发的目标服务质量参数进行比较，当预测服务质量参数与目标服务质量参数(即实际的服务质量参数)不相同时，可以通过参数预测通知功能调用分析预测接口，进而可以通过分析预测接口将预测服务质量参数或者是预测服务质量参数超过门限值的通知信息发送至应用程序客户端。其中，应用程序客户端和分析预测功能组件的交互过程可以参见上述图6所对应的实施例。可选的，在比较预测服务质量参数和目标服务质量参数时，可以考虑基于置信度的判断，例如，分析预测功能组件可以计算出该预测服务质量参数对应的置信度，若该置信度大于比较阈值，则可以认为预测服务质量参数与目标服务质量参数不相同，即预测到目标服务质量参数很有可能发生变化(具有较大的变化趋势)，其中，比较阈值可以根据实际需要进行设置，本申请实施例对此不做限定。
在本申请实施例中，通过签约参数预测通知功能，可以支持分析预测功能组件主动为应用程序客户端预测相关的服务质量参数，以使后续该应用程序客户端可以基于预测得到的服务质量参数进行适应性调整，从而可以在服务质量机制中拓展应用程序客户端获取并使用预测服务质量参数的能力。
请一并参见图9，图9是本申请实施例提供的一种数据处理方法的流程示意图。该数据处理方法可以由会话管理网元、终端设备(包括分析预测功能组件)以及运行在该终端设设备上的应用程序客户端共同执行。如图9所示，该数据处理方法至少可以包括以下步骤：
S701，当建立协议数据单元会话时，会话管理网元可以向终端设备下发服务质量规则以及服务质量参数集。
S702，终端设备接收到服务质量规则以及服务质量参数集后，可以基于服务质量规则，将协议数据单元会话对应的应用程序客户端所发送的业务数据包映射至服务质量流，具体过程可以参见上述图3所对应实施例中的S102，这里不再进行赘述。
S703，终端设备可以生成第二功能指令，并将其发送至会话管理网元，以向会话管理网元指示该终端设备是否支持分析预测功能组件的分析预测功能。
S704，会话管理网元接收到第二功能指令后，可以对第二功能指令进行判断。若第二功能指令为功能支持指令，则会话管理网元可以基于功能指示信息生成第一功能指令，其中，功能指示信息包括但不限于终端设备的签约信息、协议数据单元会话发起时携带的数据网络名称和单个网络切片选择辅助信息、运营商自己的配置以及网络策略中的一种或多种。其中，第一功能指令可以为功能开放指令或功能关闭指令。
可选的，若第二功能指令为功能不支持指令，或者，终端设备没有发送第二功能指令，则会话管理网元可以不用生成第一功能指令。
S705，会话管理网元可以将生成的第一功能指令下发至终端设备。
S706，应用程序客户端可以向终端设备上的分析预测功能组件发送参数预测请求。
S707，终端设备接收到参数预测请求时，可以先对第一功能指令进行判断。若第一功能指令为功能开放指令，则分析预测功能组件可以为应用程序客户端预测服务质量流所对应的预测服务质量参数，具体过程可以参见上述图5所对应实施例中的S303。
S708，终端设备上的分析预测功能组件可以通过分析预测接口将预测服务质量参数发送至应用程序客户端。
S709，若第一功能指令为功能关闭指令，则终端设备上的分析预测功能组件可以生成请求拒绝信息。该请求拒绝信息针对于参数预测请求。
S710，终端设备上的分析预测功能组件可以通过分析预测接口将请求拒绝信息发送至应用程序客户端。
S711，应用程序客户端可以向分析预测功能组件签约参数预测通知功能。
S712，当预测到目标服务质量参数具有变化趋势或者预测服务质量参数超过门限值时，终端设备上的分析预测功能组件可以基于参数预测通知功能重新为应用程序客户端预测对应的服务质量参数，或者，将预测服务质量参数超过门限值的通知信息发送至应用程序客户端。
S713，终端设备上的分析预测功能组件可以通过分析预测接口将重新预测得到的服务质量参数下发至终端设备。可选的，分析预测功能组件也可以先向应用程序客户端发送参数变化通知消息，随后应用程序客户端可以基于参数变化通知消息重新发起参数预测请求，最终可以获取重新预测得到的服务质量参数。
在本申请实施例中，通过应用程序客户端、终端设备、分析预测功能组件以及会话管理网元之间的交互，可以为运行在该终端设备上的应用程序客户端预测相关的服务质量参数，此外，当分析预测功能组件预测到目标服务质量参数具有变化趋势或者预测服务质量参数超过门限值时，也可以为该应用程序客户端重新预测可能变化的服务质量参数，以使后续该应用程序客户端可以基于预测得到的服务质量参数进行适应性调整，从而可以在服务质量机制中拓展应用程序客户端获取并使用预测服务质量参数的能力。
请参见图10，是本申请实施例提供的一种数据处理装置的结构示意图。该数据处理装置可以是运行于计算机设备的一个计算机程序(包括程序代码)，例如该数据处理装置为一个应用软件；该装置可以用于执行本申请实施例提供的数据处理方法中的相应步骤。如图10所示，该数据处理装置1可以运行于终端设备，该终端设备可以为上述图2所对应实施例中的终端设备A。该数据处理1可以包括：请求发送模块11、分析预测功能模块12；
请求发送模块11，用于将参数预测请求发送至分析预测功能模块12；参数预测请求是由应用程序客户端生成的；应用程序客户端运行在终端设备中；
分析预测功能模块12，用于基于参数预测请求为应用程序客户端预测服务质量流所对应的预测服务质量参数，将预测服务质量参数发送至应用程序客户端；服务质量流与应用 程序客户端所提供的业务数据包相关联。
其中，请求发送模块11的具体功能实现方式可以参见上述图3所对应实施例中的S101，分析预测功能模块12的具体功能实现方式可以参见上述图3所对应实施例中的S102，这里不再进行赘述。其中，这里的分析预测功能模块12即为上述图3所对应实施例中的分析预测功能组件。
请一并参见图10，该数据处理装置1还可以包括：映射模块13；
映射模块13，用于接收会话管理网元下发的服务质量规则以及服务质量参数集，基于服务质量规则，将应用程序客户端所发送的业务数据包映射至服务质量流；服务质量参数集包括与服务质量流相关联的目标服务质量参数。
其中，映射模块13的具体功能实现方式可以参见上述图3所对应实施例中的S102，这里不再进行赘述。
请一并参见图10，该数据处理装置1还可以包括：通知签约模块14、重新请求模块15；
通知签约模块14，用于向分析预测功能模块12签约与应用程序客户端相关联的参数预测通知功能；
则上述分析预测功能模块12，还用于当预测到目标服务质量参数具有变化趋势或者预测服务质量参数超过门限值时，基于参数预测通知功能生成参数变化通知消息，将参数变化通知消息发送至应用程序客户端；
重新请求模块15，用于发送参数预测请求；参数预测请求是由应用程序客户端基于参数变化通知消息重新生成的。
其中，通知签约模块14、重新请求模块15、分析预测功能模块12的具体功能实现方式可以参见上述图5所对应实施例中的S304，这里不再进行赘述。
请一并参见图10，该数据处理装置1还可以包括：指令获取模块16；
指令获取模块16，用于获取移动核心网网元下发的第一功能指令；
则上述分析预测功能模块12，还用于若第一功能指令为功能开放指令，则执行基于参数预测请求为应用程序客户端预测服务质量流所对应的预测服务质量参数的步骤；功能开放指令指示终端设备向应用程序客户端开放分析预测功能模块12的分析预测功能。
其中，上述移动核心网网元可以为会话管理网元。
其中，指令获取模块16、分析预测功能模块12的具体功能实现方式可以参见上述图5所对应实施例中的S301以及S303，这里不再进行赘述。
请一并参见图10，上述分析预测功能模块12，还用于若第一功能指令为功能关闭指令，则向应用程序客户端发送针对参数预测请求的请求拒绝信息；功能关闭指令指示终端设备不向应用程序客户端开放分析预测功能模块12的分析预测功能。
其中，分析预测功能模块12的具体功能实现方式可以参见上述图5所对应实施例中的S305，这里不再进行赘述。
请一并参见图10，该数据处理装置1还可以包括：功能支持模块17；
功能支持模块17，用于将第二功能指令发送至移动核心网网元；若第二功能指令为功能支持指令，则执行获取移动核心网网元下发的第一功能指令的步骤；功能支持指令指示 终端设备支持分析预测功能模块12的分析预测功能。
其中，接口支持模块17的具体功能实现方式可以参见上述图7所对应实施例中的S501，这里不再进行赘述。
请一并参见图10，上述分析预测功能模块12可以包括：第一识别单元121、第一预测单元122、第一发送单元123；
第一识别单元121，用于根据参数预测请求获取与应用程序客户端相关联的服务质量流标识，识别服务质量流标识对应的服务质量流；
第一预测单元122，用于基于目标服务质量参数对应的历史参数信息，预测服务质量流对应的预测服务质量参数；
上述第一预测单元122，具体用于将目标服务质量参数对应的历史参数信息输入参数预测模型，通过参数预测模型提取历史参数信息对应的参数变化特征，基于参数变化特征对目标服务质量参数进行调整，得到服务质量流对应的预测服务质量参数；
第一发送单元123，用于将预测服务质量参数发送至应用程序客户端；
在一种实施方式中，应用程序客户端为执行流媒体业务的客户端；
第一发送单元123，具体用于向应用程序客户端发送包含预测服务质量参数的参数预测响应消息，以使应用程序客户端基于预测服务质量参数对编码算法进行调整，且基于调整后的编码算法以及流媒体数据，生成优化的业务数据包。
其中，第一识别单元121、第一预测单元122、第一发送单元123的具体功能实现方式可以参见上述图3所对应实施例中的S102，这里不再进行赘述。
请一并参见图10，上述分析预测功能模块12可以包括：第二识别单元124、第二预测单元125、第二发送单元126；
第二识别单元124，用于根据参数预测请求获取与应用程序客户端相关联的网络切片选择辅助信息，识别网络切片选择辅助信息对应的网络切片；
第二预测单元125，用于基于服务质量参数集中与网络切片相关联的服务质量参数对应的历史参数信息，预测服务质量流对应的预测服务质量参数；网络切片相关联的服务质量参数包括目标服务质量参数；
第二发送单元126，用于将预测服务质量参数发送至应用程序客户端；
在一种实施方式中，应用程序客户端为执行流媒体业务的客户端；
第二发送单元126，具体用于向应用程序客户端发送包含预测服务质量参数的参数预测响应消息，以使应用程序客户端基于预测服务质量参数对编码算法进行调整，且基于调整后的编码算法以及流媒体数据，生成优化的业务数据包。
其中，第二识别单元124、第二预测单元125、第二发送单元126的具体功能实现方式可以参见上述图3所对应实施例中的S102，这里不再进行赘述。
本申请实施例可以支持终端设备上协议数据单元会话对应的应用程序客户端向分析预测功能组件发送参数预测请求，进而分析预测功能组件可以基于该参数预测请求为应用程序客户端预测服务质量流所对应的预测服务质量参数，最终可以将预测服务质量参数发送至应用程序客户端。由此可见，分析预测功能组件可以响应运行在该终端设备上的应用程 序客户端发送的参数预测请求，为该应用程序客户端预测相应的服务质量参数，以使后续该应用程序客户端可以基于预测服务质量参数进行适应性调整，从而可以在服务质量机制中拓展应用程序客户端获取并使用预测服务质量参数的能力。
请参见图11，是本申请实施例提供的一种数据处理装置的结构示意图。该数据处理装置可以是运行于计算机设备的一个计算机程序(包括程序代码)，例如该数据处理装置为一个应用软件；该装置可以用于执行本申请实施例提供的数据处理方法中的相应步骤。如图11所示，该数据处理装置2可以运行于终端设备，该终端设备可以为上述图2所对应实施例中的终端设备A。该数据处理2可以包括：签约模块21、分析预测功能模块22；
签约模块21，用于向分析预测功能模块签约与应用程序客户端相关联的参数预测通知功能；应用程序客户端为协议数据单元会话对应的客户端，应用程序客户端运行于终端设备中；
分析预测功能模块22，用于基于参数预测通知功能为应用程序客户端预测服务质量流所对应的预测服务质量参数；服务质量流与应用程序客户端提供的业务数据包相关联；
分析预测功能模块22，还用于当预测服务质量参数与目标服务质量参数不相同或者预测服务质量参数超过门限值时，将预测服务质量参数发送至应用程序客户端；目标服务质量参数是由会话管理网元所下发的。
其中，签约模块21的具体功能实现方式可以参见上述图8所对应实施例中的S601，分析预测功能模块22的具体功能实现方式可以参见上述图8所对应实施例中的S602-S603，这里不再进行赘述。其中，这里的分析预测功能模块22即为上述图8所对应实施例中的分析预测功能组件。
在本申请实施例中，通过签约参数预测通知功能，可以支持分析预测功能组件主动为应用程序客户端预测相关的服务质量参数，以使后续该应用程序客户端可以基于预测得到的服务质量参数进行适应性调整，从而可以在服务质量机制中拓展应用程序客户端获取并使用预测服务质量参数的能力。
请参见图12，是本申请实施例提供的一种网元装置的结构示意图。该网元装置可以是运行于网元设备的一个计算机程序(包括程序代码)，例如该网元装置为一个应用软件；该装置可以用于执行本申请实施例提供的数据处理方法中的相应步骤。如图12所示，该网元装置3可以运行于会话管理网元。该网元装置3可以包括：下发模块31；
下发模块31，用于向终端设备下发服务质量规则以及服务质量参数集，以使终端设备基于服务质量规则，将协议数据单元会话对应的应用程序客户端所发送的业务数据包映射至服务质量流；终端设备包括应用程序客户端和分析预测功能组件，应用程序客户端具有生成参数预测请求的功能，参数预测请求指示分析预测功能组件将服务质量流对应的预测服务质量参数发送至应用程序客户端，预测服务质量参数是由分析预测功能组件基于参数预测请求为业务数据包所预测得到的；服务质量参数集包括与目标服务质量参数。
其中，下发模块31的具体功能实现方式可以参见上述图9所对应实施例中的S701，这里不再进行赘述。
请一并参见图12，该网元装置3还可以包括：指令生成模块32；
指令生成模块32，用于基于功能指示信息生成第一功能指令，将第一功能指令下发至终端设备；第一功能指令为功能开放指令或功能关闭指令；功能开放指令指示终端设备向应用程序客户端开放分析预测功能组件的分析预测功能；功能关闭指令指示终端设备不向应用程序客户端开放分析预测功能组件的分析预测功能。
其中，指令生成模块32的具体功能实现方式可以参见上述图9所对应实施例中的S704，这里不再进行赘述。
请一并参见图12，该网元装置3还可以包括：指令获取模块33；
指令获取模块33，用于获取终端设备发送的第二功能指令；若第二功能指令为功能支持指令，则执行基于功能指示信息生成第一功能指令的步骤；功能支持指令指示终端设备支持分析预测功能组件的分析预测功能。
其中，指令获取模块33的具体功能实现方式可以参见上述图9所对应实施例中的S703-S704，这里不再进行赘述。
在本申请实施例中，通过应用程序客户端、终端设备、分析预测功能组件以及会话管理网元之间的交互，可以为运行在该终端设备上的应用程序客户端预测相关的服务质量参数，此外，当分析预测功能组件预测到目标服务质量参数具有变化趋势或者预测服务质量参数超过门限值时，也可以为该应用程序客户端重新预测可能变化的服务质量参数，以使后续该应用程序客户端可以基于预测得到的服务质量参数进行适应性调整，从而可以在服务质量机制中拓展应用程序客户端获取并使用预测服务质量参数的能力。
请参见图13，是本申请实施例提供的一种计算机设备的结构示意图。如图13所示，该计算机设备1000可以包括：处理器1001，网络接口1004和存储器1005，此外，上述计算机设备1000还可以包括：用户接口1003，和至少一个通信总线1002。其中，通信总线1002用于实现这些组件之间的连接通信。其中，用户接口1003可以包括显示屏(Display)、键盘(Keyboard)，可选用户接口1003还可以包括标准的有线接口、无线接口。网络接口1004可选的可以包括标准的有线接口、无线接口(如WI-FI接口)。存储器1004可以是高速RAM存储器，也可以是非不稳定的存储器(non-volatile memory)，例如至少一个磁盘存储器。存储器1005可选的还可以是至少一个位于远离前述处理器1001的存储装置。如图13所示，作为一种计算机可读存储介质的存储器1005中可以包括操作系统、网络通信模块、用户接口模块以及设备控制应用程序。在本申请实施例中，计算机设备1000可以为终端设备。
在如图13所示的计算机设备1000中，网络接口1004可提供网络通讯功能；而用户接口1003主要用于为用户提供输入的接口；而处理器1001可以用于调用存储器1005中存储的设备控制应用程序，以使该计算机设备1000执行前文图3、图5、图7、图8、图9任一个所对应实施例中对该数据处理方法的描述，也可执行前文图10所对应实施例中对该数据处理装置1或者图11所对应实施例中对该数据处理装置2的描述，在此不再赘述。另外，对采用相同方法的有益效果描述，也不再进行赘述。
请参见图14，是本申请实施例提供的一种网元设备的结构示意图。如图14所示，该网元设备2000可以包括：处理器2001，网络接口2003和存储器2004，此外，上述网元设备2000还可以包括：至少一个通信总线2002。其中，通信总线2002用于实现这些组件之间的连接 通信。其中，网络接口2003可选的可以包括标准的有线接口、无线接口(如WI-FI接口)。存储器2004可以是高速RAM存储器，也可以是非不稳定的存储器(non-volatile memory)，例如至少一个磁盘存储器。存储器2004可选的还可以是至少一个位于远离前述处理器2001的存储装置。如图14所示，作为一种计算机可读存储介质的存储器2004中可以包括操作系统、网络通信模块以及设备控制应用程序。在本申请实施例中，网元设备2000可以为会话管理网元。
在如图14所示的网元设备2000中，网络接口2003可提供网络通讯功能；而处理器2001可以用于调用存储器2004中存储的设备控制应用程序，以使该网元设备2000执行前文图9所对应实施例中对该数据处理方法的描述，也可执行前文图12所对应实施例中对该网元装置3的描述，在此不再赘述。另外，对采用相同方法的有益效果描述，也不再进行赘述。
此外，这里需要指出的是：本申请实施例还提供了一种计算机可读存储介质，且上述计算机可读存储介质中存储有前文提及的数据处理装置1或者数据处理装置2或者网元装置3所执行的计算机程序，且上述计算机程序包括程序指令，当上述处理器执行上述程序指令时，能够执行前文图3、图5、图7、图8、图9任一个所对应实施例中对上述数据处理方法的描述，因此，这里将不再进行赘述。另外，对采用相同方法的有益效果描述，也不再进行赘述。对于本申请所涉及的计算机可读存储介质实施例中未披露的技术细节，请参照本申请方法实施例的描述。
上述计算机可读存储介质可以是前述任一实施例提供的数据处理装置或网元装置或者上述计算机设备或网元设备的内部存储单元，例如计算机设备的硬盘或内存。该计算机可读存储介质也可以是该计算机设备(或网元设备)的外部存储设备，例如该计算机设备上配备的插接式硬盘，智能存储卡(smart media card，SMC)，安全数字(secure digital，SD)卡，闪存卡(flash card)等。进一步地，该计算机可读存储介质还可以既包括该计算机设备(或网元设备)的内部存储单元也包括外部存储设备。该计算机可读存储介质用于存储该计算机程序以及该计算机设备(或网元设备)所需的其他程序和数据。该计算机可读存储介质还可以用于暂时地存储已经输出或者将要输出的数据。
此外，这里需要指出的是：本申请实施例还提供了一种计算机程序产品或计算机程序，该计算机程序产品或计算机程序包括计算机指令，该计算机指令存储在计算机可读存储介质中。计算机设备的处理器从计算机可读存储介质读取该计算机指令，处理器执行该计算机指令，使得该计算机设备执行前文图3、图5、图7、图8、图9任一个所对应实施例提供的方法。此外，网元设备的处理器也可以从计算机可读存储介质读取该计算机指令，处理器执行该计算机指令，使得该网元设备执行前文图9所对应实施例提供的方法。
进一步的，请参见图15，图15是本申请实施例提供的一种数据处理系统的结构示意图。该数据处理系统4可以包含数据处理装置1a、数据处理装置2a以及网元装置3a。其中，数据处理装置1a可以为上述图10所对应实施例中的数据处理装置1，可以理解的是，该数据处理装置1a可以集成在上述图2所对应实施例中的终端设备A，因此，这里将不再进行赘述。其中，数据处理装置2a可以为上述图11所对应实施例中的数据处理装置2，可以理解的是，该数据处理装置2a可以集成在上述图2所对应实施例中的终端设备A，因此，这里将不再进行 赘述。其中，网元装置3a可以为上述图12所对应实施例中的网元装置3，因此，这里将不再进行赘述。另外，对采用相同方法的有益效果描述，也不再进行赘述。对于本申请所涉及的数据处理系统实施例中未披露的技术细节，请参照本申请方法实施例的描述。
本申请实施例的说明书和权利要求书及附图中的术语“第一”、“第二”等是用于区别不同对象，而非用于描述特定顺序。此外，术语“包括”以及它们任何变形，意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、装置、产品或设备没有限定于已列出的步骤或模块，而是可选地还包括没有列出的步骤或模块，或可选地还包括对于这些过程、方法、装置、产品或设备固有的其他步骤单元。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、计算机软件或者二者的结合来实现，为了清楚地说明硬件和软件的可互换性，在上述说明中已经按照功能一般性地描述了各示例的组成及步骤。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
以上所揭露的仅为本申请较佳实施例而已，当然不能以此来限定本申请之权利范围，因此依本申请权利要求所作的等同变化，仍属本申请所涵盖的范围。

Claims (19)

  1. 一种数据处理方法，所述方法由终端设备执行，所述终端设备包括应用程序客户端和分析预测功能组件，所述方法包括：
    所述应用程序客户端生成参数预测请求，将所述参数预测请求发送至所述分析预测功能组件；
    所述分析预测功能组件基于所述参数预测请求，为所述应用程序客户端预测服务质量流所对应的预测服务质量参数，将所述预测服务质量参数发送至所述应用程序客户端；所述服务质量流与所述应用程序客户端所提供的业务数据包相关联。
  2. 根据权利要求1所述的方法，还包括：
    所述终端设备接收会话管理网元下发的服务质量规则以及服务质量参数集，基于所述服务质量规则，将所述应用程序客户端所发送的业务数据包映射至所述服务质量流；所述服务质量参数集包括与所述服务质量流相关联的目标服务质量参数。
  3. 根据权利要求2所述的方法，所述分析预测功能组件基于所述参数预测请求为所述应用程序客户端预测服务质量流所对应的预测服务质量参数，将所述预测服务质量参数发送至所述应用程序客户端，包括：
    所述分析预测功能组件根据所述参数预测请求获取与所述应用程序客户端相关联的服务质量流标识，所述服务质量流标识用于标识对应的所述服务质量流；
    所述分析预测功能组件基于所述目标服务质量参数对应的历史参数信息，预测所述服务质量流对应的预测服务质量参数；
    所述分析预测功能组件将所述预测服务质量参数发送至所述应用程序客户端。
  4. 根据权利要求3所述的方法，所述分析预测功能组件基于所述目标服务质量参数对应的历史参数信息，预测所述服务质量流对应的预测服务质量参数，包括：
    所述分析预测功能组件将所述目标服务质量参数对应的历史参数信息输入参数预测模型，通过所述参数预测模型提取所述历史参数信息对应的参数变化特征，基于所述参数变化特征对所述目标服务质量参数进行调整，得到所述服务质量流对应的预测服务质量参数。
  5. 根据权利要求2所述的方法，所述分析预测功能组件基于所述参数预测请求为所述应用程序客户端预测服务质量流所对应的预测服务质量参数，将所述预测服务质量参数发送至所述应用程序客户端，包括：
    所述分析预测功能组件根据所述参数预测请求获取与所述应用程序客户端相关联的网络切片选择辅助信息，识别所述网络切片选择辅助信息对应的网络切片；
    所述分析预测功能组件基于所述服务质量参数集中与所述网络切片相关联的服务质量参数对应的历史参数信息，预测所述服务质量流对应的预测服务质量参数；所述网络切片相关联的服务质量参数包括所述目标服务质量参数；
    所述分析预测功能组件将所述预测服务质量参数发送至所述应用程序客户端。
  6. 根据权利要求3所述的方法，还包括：
    所述应用程序客户端向所述分析预测功能组件签约参数预测通知功能；
    当所述分析预测功能组件预测到所述目标服务质量参数具有变化趋势或者所述预测服 务质量参数超过门限值时，所述分析预测功能组件基于所述参数预测通知功能生成参数变化通知消息，将所述参数变化通知消息发送至所述应用程序客户端；
    所述应用程序客户端基于所述参数变化通知消息重新发起参数预测请求。
  7. 根据权利要求1所述的方法，还包括：
    所述终端设备获取移动核心网网元下发的第一功能指令；
    若所述第一功能指令为功能开放指令，则所述分析预测功能组件执行所述基于所述参数预测请求，为所述应用程序客户端预测服务质量流所对应的预测服务质量参数的步骤；所述功能开放指令指示所述终端设备向所述应用程序客户端开放所述分析预测功能组件的分析预测功能。
  8. 根据权利要求7所述的方法，还包括：
    若所述第一功能指令为功能关闭指令，则所述分析预测功能组件向所述应用程序客户端发送针对所述参数预测请求的请求拒绝信息；所述功能关闭指令指示所述终端设备不向所述应用程序客户端开放所述分析预测功能组件的分析预测功能。
  9. 根据权利要求7所述的方法，还包括：
    所述终端设备将第二功能指令发送至所述移动核心网网元；
    若所述第二功能指令为功能支持指令，则所述终端设备执行所述获取移动核心网网元下发的第一功能指令的步骤；所述功能支持指令指示所述终端设备支持所述分析预测功能组件的分析预测功能。
  10. 根据权利要求7所述的方法，所述移动核心网网元为会话管理网元。
  11. 根据权利要求3或5所述的方法，所述应用程序客户端为执行流媒体业务的客户端；
    所述将所述预测服务质量参数发送至所述应用程序客户端，包括：
    所述分析预测功能组件向所述应用程序客户端发送包含所述预测服务质量参数的参数预测响应消息，以使所述应用程序客户端基于所述预测服务质量参数对编码算法进行调整，且基于调整后的编码算法以及流媒体数据，生成优化的业务数据包。
  12. 一种数据处理方法，所述方法由终端设备执行，所述终端设备包括应用程序客户端和分析预测功能组件，所述方法包括：
    所述应用程序客户端向所述分析预测功能组件签约针对协议数据单元会话的参数预测通知功能；所述协议数据单元会话与所述应用程序客户端提供的业务数据包相关联；
    所述分析预测功能组件基于所述参数预测通知功能为所述应用程序客户端预测服务质量流所对应的预测服务质量参数；所述服务质量流与所述业务数据包相关联；
    当所述预测服务质量参数与所述服务质量流相关联的服务质量参数不相同或者所述预测服务质量参数超过门限值时，所述分析预测功能组件将所述预测服务质量参数发送至所述应用程序客户端；所述服务质量流相关联的服务质量参数是由会话管理网元所下发的。
  13. 一种数据处理方法，所述方法由会话管理网元执行，所述方法包括：
    向终端设备下发服务质量规则以及服务质量参数集，以使所述终端设备基于所述服务质量规则，将应用程序客户端所发送的业务数据包映射至服务质量流；所述终端设备包括所述应用程序客户端和分析预测功能组件，所述应用程序客户端具有生成参数预测请求的 功能，所述参数预测请求指示所述分析预测功能组件将所述服务质量流对应的预测服务质量参数发送至所述应用程序客户端，所述预测服务质量参数是由所述分析预测功能组件基于所述参数预测请求为所述业务数据包所预测得到的；所述服务质量参数集包括与所述服务质量流相关联的目标服务质量参数。
  14. 根据权利要求13所述的方法，还包括：
    基于功能指示信息生成第一功能指令，将所述第一功能指令下发至所述终端设备；所述第一功能指令为功能开放指令或功能关闭指令；所述功能开放指令指示所述终端设备向所述应用程序客户端开放所述分析预测功能组件的分析预测功能；所述功能关闭指令指示所述终端设备不向所述应用程序客户端开放所述分析预测功能组件的分析预测功能。
  15. 根据权利要求14所述的方法，还包括：
    获取所述终端设备发送的第二功能指令；
    若所述第二功能指令为功能支持指令，则执行所述基于功能指示信息生成第一功能指令的步骤；所述功能支持指令指示所述终端设备支持所述分析预测功能组件的分析预测功能。
  16. 一种计算机设备，包括：处理器、存储器以及网络接口；
    所述处理器与所述存储器、所述网络接口相连，其中，所述网络接口用于提供数据通信功能，所述存储器用于存储程序代码，所述处理器用于调用所述程序代码，以使所述计算机设备执行权利要求1-12任一项所述的方法。
  17. 一种网元设备，包括：处理器、存储器以及网络接口；
    所述处理器与所述存储器、所述网络接口相连，其中，所述网络接口用于提供数据通信功能，所述存储器用于存储程序代码，所述处理器用于调用所述程序代码，以使所述网元设备执行权利要求13-15任一项所述的方法。
  18. 一种计算机可读存储介质，所述计算机可读存储介质中存储有计算机程序，所述计算机程序适于由处理器加载并执行权利要求1-15任一项所述的方法。
  19. 一种包括指令的计算机程序产品，当其在计算机上运行时，使得所述计算机执行权利要求1-15任一项所述的方法。
PCT/CN2022/113279 2021-09-10 2022-08-18 一种数据处理方法、设备、可读存储介质和程序产品 WO2023035895A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP22866368.8A EP4231703A4 (en) 2021-09-10 2022-08-18 DATA PROCESSING METHOD, DEVICE, READABLE STORAGE MEDIUM AND PROGRAM PRODUCT
US18/197,498 US20230283529A1 (en) 2021-09-10 2023-05-15 Data processing method and device, readable storage medium and program product

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111061875.9 2021-09-10
CN202111061875.9A CN113784397A (zh) 2021-09-10 2021-09-10 一种数据处理方法、设备以及可读存储介质

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/197,498 Continuation US20230283529A1 (en) 2021-09-10 2023-05-15 Data processing method and device, readable storage medium and program product

Publications (1)

Publication Number Publication Date
WO2023035895A1 true WO2023035895A1 (zh) 2023-03-16

Family

ID=78842380

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/113279 WO2023035895A1 (zh) 2021-09-10 2022-08-18 一种数据处理方法、设备、可读存储介质和程序产品

Country Status (4)

Country Link
US (1) US20230283529A1 (zh)
EP (1) EP4231703A4 (zh)
CN (1) CN113784397A (zh)
WO (1) WO2023035895A1 (zh)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113784396A (zh) * 2021-09-10 2021-12-10 腾讯科技（深圳）有限公司 一种数据处理方法、设备以及可读存储介质
CN113784397A (zh) * 2021-09-10 2021-12-10 腾讯科技（深圳）有限公司 一种数据处理方法、设备以及可读存储介质
CN114710811A (zh) * 2022-04-07 2022-07-05 中国联合网络通信集团有限公司 数据流转发方法、装置、电子设备及存储介质
CN115086940B (zh) * 2022-05-13 2023-06-06 广州爱浦路网络技术有限公司 基于5G的QoS调整方法、系统、装置及存储介质
US11973690B2 (en) * 2022-10-04 2024-04-30 Palo Alto Networks, Inc. Application precedence based traffic policy enforcement

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110661837A (zh) * 2018-06-30 2020-01-07 华为技术有限公司 服务质量的控制方法和装置
WO2020060334A1 (en) * 2018-09-20 2020-03-26 Lg Electronics Inc. Method and apparatus for performing qos prediction in nr v2x
CN110996302A (zh) * 2018-10-02 2020-04-10 大众汽车有限公司 预测通信设备的通信链路的通信的服务质量的方法和装置
CN112566164A (zh) * 2020-12-09 2021-03-26 广州虎牙科技有限公司 一种通信系统及服务质量控制方法
CN113784397A (zh) * 2021-09-10 2021-12-10 腾讯科技（深圳）有限公司 一种数据处理方法、设备以及可读存储介质

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10277515B2 (en) * 2016-04-04 2019-04-30 Qualcomm Incorporated Quality of service (QOS) management in wireless networks
US10986516B2 (en) * 2017-03-10 2021-04-20 Huawei Technologies Co., Ltd. System and method of network policy optimization
CN112740623B (zh) * 2018-09-17 2022-08-19 华为技术有限公司 用于提供服务质量功能的设备和方法
US11678252B2 (en) * 2018-10-05 2023-06-13 Huawei Technologies Co., Ltd. Quality of service information notification to user equipment, users, and application server
WO2020147927A1 (en) * 2019-01-15 2020-07-23 Huawei Technologies Co., Ltd. Methods and nodes for in-advance qos prediction notification
US20210112441A1 (en) * 2020-12-23 2021-04-15 Dario Sabella Transportation operator collaboration system

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110661837A (zh) * 2018-06-30 2020-01-07 华为技术有限公司 服务质量的控制方法和装置
WO2020060334A1 (en) * 2018-09-20 2020-03-26 Lg Electronics Inc. Method and apparatus for performing qos prediction in nr v2x
CN110996302A (zh) * 2018-10-02 2020-04-10 大众汽车有限公司 预测通信设备的通信链路的通信的服务质量的方法和装置
CN112566164A (zh) * 2020-12-09 2021-03-26 广州虎牙科技有限公司 一种通信系统及服务质量控制方法
CN113784397A (zh) * 2021-09-10 2021-12-10 腾讯科技（深圳）有限公司 一种数据处理方法、设备以及可读存储介质

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
ERICSSON: "Pseudo-CR on QoS notifications to V2X UE", 3GPP DRAFT; S6-200385, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, vol. SA WG6, no. E-meeting; 20200224 - 20200228, 18 February 2020 (2020-02-18), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France , XP051855176 *
See also references of EP4231703A4

Also Published As

Publication number Publication date
CN113784397A (zh) 2021-12-10
US20230283529A1 (en) 2023-09-07
EP4231703A1 (en) 2023-08-23
EP4231703A4 (en) 2024-04-24

Similar Documents

Publication Publication Date Title
WO2023035895A1 (zh) 一种数据处理方法、设备、可读存储介质和程序产品
WO2023035894A1 (zh) 一种数据处理方法、设备、可读存储介质和程序产品
CN109417534B (zh) 通信网络服务质量能力开放方法和装置
KR101489414B1 (ko) 통신 네트워크에서 패킷을 우선순위결정 및 스케줄링하기 위한 검출 방법 및 시스템
US9749234B2 (en) Signaling-less dynamic call setup and teardown by utilizing observed session state information
KR102013729B1 (ko) 통신 네트워크에서 애플리케이션-인식 수락 제어를 위한 방법 및 시스템
US9538220B2 (en) Video streaming quality of experience degradation control using a video quality metric
US20130298170A1 (en) Video streaming quality of experience recovery using a video quality metric
US20130290492A1 (en) State management for video streaming quality of experience degradation control and recovery using a video quality metric
US20120281536A1 (en) Systems and methods for detection for prioritizing and scheduling packets in a communication network
US20120327779A1 (en) Systems and methods for congestion detection for use in prioritizing and scheduling packets in a communication network
Akyildiz et al. XStream: A new platform enabling communication between applications and the 5G network
CN104472006B (zh) 用于通信系统中的协作应用的系统和方法
US10581944B2 (en) Transmission resource distribution for streaming of variable bitrate encoded media data
CN114079932B (zh) 5g网络质量保障系统及方法
Ramamurthi et al. Video-QoE aware resource management at network core
KR102234927B1 (ko) 협력형 통신 시스템 내 애플리케이션 품질 관리
WO2014209495A1 (en) Video streaming quality of experience recovery using a video quality metric
US11627358B2 (en) Communication entity and a method for transmitting a video data stream
Khan et al. QoE-based video delivery over LTE hierarchical architecture
CN113630778B (zh) 一种QoS流的动态控制方法及终端
US8437767B2 (en) Apparatuses, method and computer program for adapting a telecommunication service to traffic load in the network
Longhao Innovative content delivery solutions in the future network heterogeneous environment
CN113938468A (zh) 视频传输方法、设备、系统及存储介质

Legal Events

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

Ref document number: 22866368

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022866368

Country of ref document: EP

Effective date: 20230515

NENP Non-entry into the national phase

Ref country code: DE