Data processing methods and apparatuses, computer-readable medium and computer device

By transmitting user plane data in mobile communication networks for network model training, the problems of signal coverage and interference are solved, and the deep integration of AI technology and mobile communication technology is achieved, thereby improving the intelligence and adaptability of the network.

WO2026232793A1PCT designated stage Publication Date: 2026-11-12TENCENT TECHNOLOGY (SHENZHEN) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2025/139449
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2025-05-09
Filing Date
2025-12-02
Publication Date
2026-11-12

AI Technical Summary

Technical Problem

When introducing AI technology into mobile communication networks, issues such as signal coverage, signal interference, and link stability between base stations and user equipment arise, making it difficult for existing technologies to effectively optimize wireless communication performance.

Method used

By transmitting user plane data between user equipment and target network elements, and using user plane functional network elements for network model training, rich training samples are provided, enabling deep integration of AI technology and mobile communication technology, and improving the accuracy and adaptability of the network model.

Benefits of technology

It has improved the functionality and flexibility of mobile communication networks, promoted the deep integration of AI technology and mobile communication technology, driven the development of edge AI models in 5G-A/6G network environments, and enhanced the intelligence and adaptability of the network.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2025139449_12112026_PF_FP_ABST
    Figure CN2025139449_12112026_PF_FP_ABST
Patent Text Reader

Abstract

Provided in the embodiments of the present application are data processing methods and apparatuses, a computer readable medium and a computer device. A data processing method comprises: acquiring user plane data sent by a user equipment, the user plane data being used for training a network model used by a mobile communication network; and sending the user plane data to a target network element, such that the target network element trains the network model on the basis of the user plane data. In the technical solutions of the embodiments of the present application, data transmission is performed by means of a user plane to provide rich training samples for the mobile communication network, thereby facilitating deep fusion of AI technology and mobile communication technology, and greatly enhancing the functionality and flexibility of the mobile communication network.
Need to check novelty before this filing date? Find Prior Art

Description

Data processing methods, apparatus, computer-readable media and computer equipment

[0001] Priority information

[0002] This application claims priority to Chinese Patent Application No. 2025106033990, filed on May 9, 2025, entitled "Data Processing Method, Apparatus, Computer-Readable Medium and Computer Equipment", the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application relates to the fields of computer and communication technology, and more specifically, to a data processing method, apparatus, computer-readable medium, and computer equipment. Background Technology

[0004] With the development of mobile communication networks, including the enhanced version of fifth-generation mobile communication technology (5G Advanced, 5G-A) and sixth-generation mobile communication system (6G), wireless communication is constantly evolving towards higher frequency bands and higher mobility. This brings with it challenges such as signal coverage, signal interference, and link stability between base stations and user equipment. Introducing artificial intelligence (AI) technology into mobile communication networks can optimize wireless communication performance to some extent; therefore, how to effectively integrate AI technology into mobile communication networks is a pressing technical problem that needs to be solved. Summary of the Invention

[0005] The embodiments of this application provide a data processing method, apparatus, computer-readable medium, and computer device, which realizes the transmission of data through the user plane to provide rich training samples for mobile communication networks, promotes the deep integration of AI technology and mobile communication technology, and greatly enhances the functionality and flexibility of mobile communication networks.

[0006] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part by practice of this application.

[0007] In a first aspect, embodiments of this application provide a data processing method, comprising: acquiring user plane data sent by a user equipment, wherein the user plane data is used to train a network model used by a mobile communication network; and sending the user plane data to a target network element so that the target network element trains the network model based on the user plane data.

[0008] Secondly, embodiments of this application provide a data processing method, including: initiating a PDU session establishment request to an access and mobility management function network element to establish a PDU session corresponding to a user equipment; collecting user plane data for training a network model used by a mobile communication network based on the PDU session; and sending the user plane data to a user plane function network element so that the user plane function network element provides the user plane data to a target network element for training the network model.

[0009] Thirdly, embodiments of this application provide a data processing apparatus, including: an acquisition unit configured to acquire user plane data sent by a user equipment, wherein the user plane data is used to train a network model used by a mobile communication network; and a transmission unit configured to send the user plane data to a target network element, so that the target network element trains the network model based on the user plane data.

[0010] Fourthly, embodiments of this application provide a data processing apparatus, comprising: a processing unit configured to initiate a PDU session establishment request to an access and mobility management function network element to establish a PDU session corresponding to a user equipment; a collection unit configured to collect user plane data for training a network model used by a mobile communication network based on the PDU session; and a sending unit configured to send the user plane data to a user plane function network element, so that the user plane function network element provides the user plane data to a target network element for network model training processing.

[0011] Fifthly, embodiments of this application provide a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the data processing method as described in the above embodiments.

[0012] Sixthly, embodiments of this application provide a computer device, including: one or more processors; and a storage device for storing one or more computer programs, which, when executed by the one or more processors, cause the computer device to implement the data processing method as described in the above embodiments.

[0013] In a seventh aspect, embodiments of this application provide a computer program product comprising a computer program stored in a computer-readable storage medium. A processor of a computer device reads from the computer-readable storage medium and executes the computer program, causing the computer device to perform the data processing methods provided in the various alternative embodiments described above.

[0014] In some embodiments of this application, the user plane function network element can acquire user plane data sent by the user equipment for training the network model used by the mobile communication network, and then send the user plane data to the target network element so that the target network element can train the network model based on the user plane data. It is evident that the technical solutions of this application enable the network model used by the mobile communication network to be trained based on the user plane data sent by the user plane function network element, thereby providing rich training samples for the mobile communication network through data transmission via the user plane. This further ensures that the trained network model can achieve more accurate traffic prediction, resource allocation, and fault diagnosis, thereby improving the intelligence and adaptability of the mobile communication network. Simultaneously, the technical solutions of this application also promote the deep integration of AI technology and mobile communication technology, driving the development of edge AI models in 5G-A / 6G network environments. This not only enhances the capabilities of existing networks but also paves the way for the development of more advanced network technologies in the future, greatly enhancing the functionality and flexibility of the mobile communication network.

[0015] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 shows a schematic diagram of the architecture of a wireless communication system provided in an embodiment of this application;

[0018] Figure 2 shows a schematic diagram of an implementation environment provided by an embodiment of this application;

[0019] Figure 3 shows a flowchart of a data processing method according to an embodiment of this application;

[0020] Figure 4 shows a flowchart of a data processing method according to an embodiment of this application;

[0021] Figure 5 shows a user plane data transmission flowchart according to an embodiment of this application;

[0022] Figure 6 illustrates a flowchart of terminating a PDU session according to an embodiment of this application;

[0023] Figure 7 shows a flowchart of terminating a PDU session according to an embodiment of this application;

[0024] Figure 8 illustrates a flowchart of terminating a PDU session according to an embodiment of this application;

[0025] Figure 9 shows a block diagram of a data processing apparatus according to an embodiment of the present application;

[0026] Figure 10 shows a block diagram of a data processing apparatus according to an embodiment of the present application;

[0027] Figure 11 shows a schematic diagram of the structure of a computer system suitable for implementing the computer device of the present application.

[0028] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. Detailed Implementation

[0029] Exemplary embodiments will now be described in a more comprehensive manner with reference to the accompanying drawings. However, the exemplary embodiments can be implemented in various forms and should not be construed as limited to these examples; rather, these embodiments are provided so that this application will be more comprehensive and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art.

[0030] Furthermore, the features, structures, or characteristics described in this application can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to provide a full understanding of the embodiments of this application. However, those skilled in the art will recognize that when implementing the technical solutions of this application, not all the detailed features in the embodiments may be used, one or more specific details may be omitted, or other methods, elements, devices, steps, etc., may be employed.

[0031] In this application embodiment, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0032] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0033] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0034] It should be noted that "multiple" in this article refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0035] The technical solution of this application mainly applies AI technology to mobile communication networks. It should be noted that AI technology uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceiving the environment, acquiring knowledge, and using that knowledge to obtain optimal results. In other words, AI is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new kind of intelligent machine that can react in a way similar to human intelligence. AI studies the design principles and implementation methods of various intelligent machines, enabling them to have perception, reasoning, and decision-making functions.

[0036] With the development of mobile communication networks such as 5G-A and 6G, wireless communication is constantly evolving towards higher frequency bands and greater mobility. This brings with it challenges such as signal coverage, signal interference, and link stability between base stations and user equipment. Introducing AI technology into mobile communication networks is a future development direction, as AI plays an increasingly important role in improving network performance, optimizing resource management, and providing personalized services. For example, edge AI models can be deployed on user equipment (UE) or application servers. These network models can perform data processing, analysis, and decision-making, and their applications are very broad, including but not limited to image recognition, speech recognition, and natural language processing. In mobile communication scenarios, optimizing wireless communication performance by deploying edge AI models on user equipment can reduce the frequency at which user equipment reports raw data to the network and avoid transmission delays caused by control commands issued by the network side, thus effectively responding to sudden traffic surges or rapid movement scenarios.

[0037] However, the introduction of AI technology into mobile communication networks (such as 5G, 5G-A, 6G, etc.) still faces many challenges. Taking a 5G system as an example, Figure 1 shows the network architecture of a 5G system, which can include a UE, access network elements, and core network elements. The UE accesses the data network (DN) through access network elements and core network elements. Specifically, the core network elements involved in the embodiments of this application include some or all of the following network elements shown in Figure 1: Access and Mobility Management Function (AMF) network elements, Session Management Function (SMF) network elements, Policy Control Function (PCF) network elements, User Plane Function (UPF) network elements, Application Function (AF) network elements, Network Exposure Function (NEF) network elements, Network Data Analytics Function (NWDAF) network elements, etc.

[0038] A DN (Network Node) can be used to deploy various services, providing data and / or voice services to terminal devices. It can also provide data services to users on IP Multimedia Service (IMS) networks, the Internet, etc. For example, a DN can be an enterprise's internal office network. Multiple application servers (AS) can be deployed within a DN to provide different application services, such as carrier services and Internet services.

[0039] In some embodiments, the core network elements may also include Unified Data Repository (UDR) network elements, Unified Data Management (UDM) network elements, Network Repository Function (NRF) network elements, Location Management Function (LMF) network elements, etc., which are not shown in Figure 1. This application does not limit these.

[0040] The following describes the core network elements involved in the embodiments of this application, namely the network functions (NFs) provided by the core network:

[0041] AMF network elements include functions such as performing mobility management and providing access authentication / authorization. They can be used to manage terminal access to the core network, such as terminal location updates, network registration, access (connection) control, reachability, terminal mobility management, and terminal attachment and detachment. They can provide session management message transmission channels for UE and SMF and are the core network control plane access points for terminals and radio.

[0042] SMF network elements include functions such as session management, execution of PCF-issued control policies, UPF selection, and Internet Protocol (IP) address allocation for terminal devices. They can be used for tunnel maintenance, selecting user plane network elements for terminals, redirecting user plane network elements for terminals, establishing bearers (also known as sessions) between terminals and UPF network elements, modifying and releasing sessions, as well as Quality of Service (QoS) control, billing data collection, roaming, etc.

[0043] PCF network elements include policy control functions such as billing at the session and service flow levels, QoS bandwidth guarantee and mobility management, and terminal device policy decisions. They can be used for a unified policy framework, providing policy rules for control plane functions. Specifically, they can be used to provide policies to AMF and SMF network elements, such as QoS policies and slice selection policies.

[0044] UPF network elements, serving as the interface with the data network, include functions such as user plane data forwarding, session / flow-level billing and statistics, and bandwidth limiting. They can be used for user data transmission, packet routing and forwarding, policy enforcement, traffic reporting, and QoS processing. UPF network elements can be referred to as user plane function network elements, while other network elements in the core network can be referred to as control plane function network elements. These elements are used for authentication, authorization, registration management, session management, mobility management, and policy control to ensure reliable and stable data transmission.

[0045] Specifically, the UPF network element can receive service data from the DN and transmit it to the UE through the access network element. The UPF network element can also receive user data from the UE through the access network element (as shown in Figure 1, the radio access network (RAN) element) and forward it to the DN. The transmission resources allocated and scheduled by the UPF network element for the terminal are managed and controlled by the SMF network element. The bearer between the UE and the UPF network element can include: the user plane connection between the UPF network element and the access network element (RAN), and the establishment of a channel between the access network element and the terminal. The user plane connection allows for the establishment of a QoS flow for data transmission between the UPF network element and the access network element (RAN).

[0046] AF (Active Front-End) network elements are used to interact with core network elements to support application data transmission, access NEF (New Front-End) network elements, or interact with PCF (Public Front-End) network elements for policy control. Specifically, they can be used to convey application-side requirements to the network side, such as QoS requirements or user state event subscriptions. AF network elements can implement control plane functions for third-party application servers, specifically through interaction between AF-NEF-PCF or AF-PCF. AF network elements can also act as AS (Application Server) elements, implementing user plane functions for third-party application servers, specifically through interaction between AS-IP transport network-UPF (User Front-End).

[0047] The NEF (Network Element) is located between the 5G core network (5GC) and external third-party AF (Action Filter) or AS (Autonomous System) network elements, responsible for exposing network data to the outside world. That is, external third-party applications need to go through the NEF to access data within the 5GC. The NEF can provide corresponding security guarantees to ensure the security of external applications accessing the 3rd Generation Partnership Project (3GPP) network, and can provide functions such as opening up QoS customization capabilities for external applications, subscription to mobility state events, and distribution of AF requests.

[0048] NWDAF (Network Data Analysis and Automated Support) network elements include functions that provide specific network data analysis services to the network. They can collect data, which may include one or more of the following: UE data, access network metadata, core network metadata, and third-party application device data. This data can be data from the UE, access network element, core network element, or third-party application device itself, or data from the UE on the access network element, core network element, or third-party application device. The NWDAF network element can perform data analysis based on the collected data and output the analysis results for use by the network, network management equipment, and applications in policy decision-making.

[0049] Specifically, NWDAF network elements can utilize machine learning models for data analysis. NWDAF network elements can be divided into training and inference function modules. An NWDAF network element supporting model training can be called an NWDAF supporting the Model Training Logic Function (MTLF), or it can be understood as an NWDAF network element including an MTLF function module. An NWDAF network element supporting model inference can be called an NWDAF supporting the Analysis Logic Function (ANLF), or it can be understood as an NWDAF network element including an ANLF function module. An NWDAF network element can integrate both MTLF and ANLF.

[0050] The ANLF can provide NWDAF service interfaces to external systems, such as the Nnwdaf_AnalyticsSubscription and Nnwdaf_AnalyticsInfo interfaces, which can generate static statistical data and / or dynamic inference results based on requests from consumer network elements. The MTLF can provide trained models to the ANLF; that is, the ANLF is a consumer network element for which the MTLF provides services. For example, the MTLF can train a model based on acquired data to obtain a trained model. Then, the ANLF can input input data into the trained model to obtain analysis results or inference data.

[0051] In some embodiments, an NWDAF network element may refer to a single network element or may be combined with other network elements, such as configuring an NWDAF into a PCF network element or an AMF network element.

[0052] Furthermore, 5G systems may also include an Analytics Data Repository Functional (ADRF) network element (not shown in Figure 1). The ADRF can be used to store data related to the NWDAF network element, such as model-related data. In the embodiments of this application, the ADRF network element can serve as a network database. The network data in the network database can be collected by the NWDAF network element for subsequent retrieval and analysis. It can also be used to store the analysis results of the NWDAF network element or other data.

[0053] It should be noted that Nnef, Npcf, Namf, Nsmf, Naf, and Nnwdaf, as shown in Figure 1, are the service interfaces provided by NEF, PCF, AMF, SMF, AF, and NWDAF, respectively, used to invoke the corresponding service operations. Specifically, N1, N2, N3, N4, and N6 are interface sequence numbers. N1 is the interface between the AMF network element and the UE; N2 is the interface between the AMF network element and the access network element; N3 is the interface between the access network element and the UPF network element; N4 is the interface between the SMF network element and the UPF network element; and N6 is the interface between the UPF network element and the DN. ANDR can provide the Nadrf interface, which can be used as a service interface for ADRF.

[0054] In some embodiments, there may be an N5 interface between the AF network element and the PCF network element, an N7 interface between the PCF network element and the SMF network element, an N11 interface between the SMF network element and the AMF network element, an N15 interface between the PCF network element and the AMF network element, and an N23 interface between the PCF network element and the NWDAF network element, etc.

[0055] It should be noted that the aforementioned network element can be a network component in a hardware device, a software function running on dedicated hardware, or a virtualization function instantiated on a platform (e.g., a cloud platform). In some embodiments, the aforementioned network element or function can be implemented by a single device, multiple devices working together, or a functional module within a single device; this application does not limit this.

[0056] Based on the system architecture of the 5G network shown in Figure 1, Figure 2 illustrates an exemplary implementation environment in which the technical solutions of the embodiments of this application can be applied. This exemplary implementation environment includes a core network (such as 5GC) 201, access network elements 202, user equipment 203, and a server 204. The core network 201 may include core network elements. Figure 2 exemplarily shows UPF, AMF, and SMF network elements. Descriptions of each element can be found in the corresponding descriptions in Figure 1, and will not be repeated here. The access network element 202, user equipment 203, and server 204 can all interact directly or indirectly with one or more core network elements in the core network 201.

[0057] Among them, the access network element 202 can be a base station (BTS) in the Global System for Mobile Communications (GSM) or Code Division Multiple Access (CDMA), a base station (Nodeb, NB) in Wideband Code Division Multiple Access (WCDMA), or a Generation Node B (gNB) in a 5G network, or a gNodeb in a New Radio (NR) system, etc.

[0058] User equipment 203 can refer to a device with wireless transceiver capabilities. It can also be referred to as a terminal, UE, mobile station (MS), mobile terminal (MT), access terminal equipment, Internet of Things terminal equipment, vehicle-mounted terminal equipment, industrial control terminal equipment, UE unit, UE station, mobile station, remote station, remote terminal equipment, mobile device, UE terminal equipment, wireless communication equipment, UE agent, or UE device, etc. For example, terminal devices can be mobile phones, tablets, desktop computers, laptops, all-in-one computers, in-vehicle terminals, virtual reality (VR) terminal devices, augmented reality (AR) terminal devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices or other processing devices connected to a wireless modem, wearable devices, terminal devices in future mobile communication networks, or terminal devices in future evolved public land mobile networks (PLMNs), etc.

[0059] In some optional embodiments, user equipment 203 can initiate a Protocol Data Unit (PDU) session establishment request to the AMF network element to establish a PDU session corresponding to user equipment 203. Then, user equipment 203 can collect user plane data for training the network model used by the mobile communication network based on this PDU session. For example, the user plane data may include network parameters collected by the access network element 202, network parameters measured by user equipment 203, etc. Afterwards, user equipment 203 can send the collected user plane data to the UPF network element. The UPF network element can then provide this user plane data to a target network element (such as server 204 or a network element in the core network) for network model training processing, according to the instructions sent by the SMF network element.

[0060] Optionally, after training the network model, the trained network model can be deployed in the user equipment 203 to optimize the wireless communication performance of the user equipment 203.

[0061] As can be seen from the above, the technical solution of this application embodiment greatly enhances the functionality of mobile communication networks through efficient user plane data collection, transmission, and utilization, laying the foundation for building a more intelligent, efficient, and reliable next-generation communication system. Simultaneously, it achieves deep integration of AI technology and mobile communication technology, promoting the development of edge AI models in mobile communication network environments (such as 5G, 5G-A, 6G, etc.). This not only improves the capabilities of existing networks but also paves the way for the research and development of more advanced network technologies in the future, such as ultra-low latency communication and large-scale IoT connections.

[0062] The implementation details of the technical solutions in the embodiments of this application are described in detail below:

[0063] Figure 3 shows a flowchart of a data processing method according to an embodiment of this application. This data processing method can be executed by a UPF or by other network elements. Referring to Figure 3, the communication method includes at least steps S310 to S330, which are described in detail below:

[0064] In S310, user plane data sent by the user equipment is acquired, wherein the user plane data is used to train the network model used by the mobile communication network.

[0065] In some optional embodiments, the network model used by the mobile communication network can be used by devices in the mobile communication network (such as user equipment, application servers, etc.) to analyze and process the network status in order to optimize the network status, improve the channel environment, and enhance the intelligence and adaptability of the mobile communication network.

[0066] Alternatively, the network model can be a Convolutional Neural Network (CNN) model, a Recurrent Neural Network (RNN) model, a lightweight model (such as MobileNet, a model optimized for mobile devices, which adapts to limited hardware resources by reducing the number of parameters and computational complexity), a reinforcement learning model, or a model based on the Transformer architecture.

[0067] In some optional embodiments, the user plane data used to train the network model used by the mobile communication network may include network state-related data, such as Reference Signal Received Power (RSRP) for evaluating signal strength, Reference Signal Received Quality (RSRQ) reflecting signal quality, Signal to Interference plus Noise Ratio (SINR) for measuring communication link quality, Received Signal Strength Indicator (RSSI) reflecting the total strength of all received signals, and Cell ID for identifying the serving cell information of the UE, etc. Alternatively, it may include location service-related measurement data, such as Time of Arrival (TOA) and Angle of Arrival (AoA).

[0068] Optionally, the user plane data used to train the network model used in the mobile communication network can be aggregated by the user equipment and then sent to the UPF.

[0069] In S320, user plane data is sent to the target network element so that the target network element can train the network model based on the user plane data.

[0070] In some optional embodiments, the target network element can be a server used for network model training. For example, the target network element can be an Over-The-Top Server (OTT Server), which is a server that provides services via the Internet. In this embodiment, it can be specifically used to receive user plane data collected from the UE and use this user plane data to train the network model. Optionally, the target network element can also be a network element in the core network, which can obtain user plane data collected by the UE by communicating with the UPF and use this user plane data to train the network model.

[0071] In some optional embodiments, the UPF can receive a transmission control configuration policy for the aforementioned user plane data sent by the session management function network element, and then send the user plane data used for training the network model to the target network element according to the transmission control configuration policy. This embodiment's technical solution enables the UPF to adjust parameters such as the priority, bandwidth allocation, and routing path of the user plane data used for training the network model according to changes in real-time network conditions and service requirements, ensuring that the user plane data used for training the network model can be transmitted to the target network element in a timely and accurate manner even under network congestion.

[0072] Optionally, the UPF can assign a Quality of Service (QoS) identifier, such as a 5G QoS Identifier (5QI), to the user plane data used for training the network model, based on the transmission control configuration policy. Then, based on the QoS identifier assigned to the user plane data, the user plane data is sent to the target network element. This embodiment enables the assignment of a dedicated QoS identifier to the user plane data used for training the network model, distinguishing it from other data. For example, other data (e.g., video streams) might use a high-bandwidth Guaranteed Bit Rate (GBR) type, while the user plane data used for training the network model might be assigned a low-priority but high-reliability Non-GBR type.

[0073] Optionally, the UPF can mark user plane data in the data to be transmitted, then allocate corresponding transmission resources to the user plane data according to the transmission control configuration policy, and use the allocated transmission resources to send the user plane data to the target network element. This embodiment's technical solution allows for the differentiation and processing of other data from user plane data used for training the network model. For example, in the UPF, traffic detection tools are used for traffic detection, and user plane data used for training the network model is marked based on traffic characteristics and allocated different transmission bandwidths than other data. Other data, if real-time, is processed first, while non-real-time data can be deferred.

[0074] In some optional embodiments, the process by which the UPF sends user plane data used for training the network model to the target network element can be as follows: The user plane data is encapsulated in a PDU session container, and the corresponding Quality of Service (QoS) control information is added to the PDU session container. Then, the PDU session container containing the encapsulated user plane data is sent to the target network element. Optionally, the QoS control information can be, for example, a QoS Flow Identifier (QFI) or a Reflective QoS Indicator (RQI). The QFI is used to uniquely identify a QoS flow. Each QoS flow represents a data channel with a specific QoS characteristic, meaning that each QoS flow has its own unique priority, latency, packet loss rate, and other characteristics. In other words, the QFI is used to distinguish data channels with different QoS characteristics in the PDU session, ensuring that each data flow is processed appropriately. The RQI is a flag used to indicate whether the network needs to apply the same QoS rules to uplink data flows as to downlink data flows. Primarily, when the network does not explicitly configure QoS rules, the corresponding uplink QoS rules can be dynamically generated through the RQI flag in the downlink data packets, thereby reducing the network configuration burden and improving efficiency.

[0075] In some alternative embodiments, an encryption algorithm can also be added to the PDU session container to encrypt the user plane data used to train the network model.

[0076] In some optional embodiments, the UPF can, upon receiving an instruction from a designated core network element instructing the transmission of user plane data, then send the user plane data used for training the network model to the target network element according to that instruction. Optionally, the designated core network element can be an SMF element or other network element. For example, the target network element can send a request message to the SMF element to request user plane data used for training the network model, and then the SMF element can send an instruction to the UPF to instruct the UPF to send the corresponding user plane data to the target network element.

[0077] In some optional embodiments, when the UPF receives an indication message sent by a designated core network element, it can send a request message to the user equipment based on the indication message to request the user equipment to send user plane data for training the network model. Then, it can execute S310 to receive the user plane data sent by the user equipment for training the network model.

[0078] In some optional embodiments, the UPF may also send the user plane data for training the network model to the target network element upon receiving it from the user equipment. In this case, the UPF performs the routing function for the user plane data, and the user equipment can send the user plane data for training the network model according to the instruction information sent by the specified core network element (such as SMF, UPF, AMF, etc.).

[0079] In some optional embodiments, the UPF can also receive a notification message sent by a session management function network element, which is used to instruct the termination of the user equipment's PDU session. The UPF can then perform at least one of the following steps based on the notification message: notify the access network element (such as a base station) to release radio resources; send a request message to the access and mobility management function network element to update the state of the PDU session; and stop forwarding user plane data.

[0080] It should be noted that terminating a user equipment's (UE) PDU session can be initiated by various network elements. For example, the UE can send a PDU session release request to the SMF network element based on service requirements (e.g., the UE detects congestion on the transmission link corresponding to the current PDU session or has completed user plane data transmission). Upon receiving the PDU session release request, the SMF network element can send the aforementioned notification message to the UPF. Similarly, an access network element can send a PDU session termination request to the SMF network element if it detects transmission link congestion. Upon receiving the PDU session termination request, the SMF network element can then send the aforementioned notification message to the UPF. Furthermore, a PCF network element can send a QoS update command to the SMF network element if it determines that radio resources are congested. This QoS update command instructs the cessation of user plane data transmission. Upon receiving this QoS update command, the SMF network element can then send the aforementioned notification message to the UPF.

[0081] Figure 3 illustrates the embodiments of this application from the perspective of the UPF. The technical solutions of the embodiments of this application are described below from the perspective of the user equipment, in conjunction with Figure 4:

[0082] Figure 4 shows a flowchart of a data processing method according to an embodiment of this application. This data processing method can be executed by a UE or by other devices. Referring to Figure 4, the communication method includes at least steps S410 to S430, which are described in detail below:

[0083] In S410, a PDU session establishment request is initiated to the access and mobility management function network element to establish a PDU session corresponding to the user equipment.

[0084] In some optional embodiments, the user equipment (UE) first completes the initial access procedure, including steps such as selecting a PLMN, random access, authentication, and encryption. Then, the UE initiates a PDU session establishment request through the AMF network element to establish a PDU session to access a specific data network. Optionally, this PDU session establishment request may include information about the target data network, such as specifying a particular OTT server as the server for network model training. Optionally, this PDU session establishment request may carry network slice information related to network model training and expected quality of service parameters, which may include, but are not limited to, latency, throughput, jitter requirements, etc., to ensure that the data transmission conditions required for network model training are met.

[0085] In S420, user plane data is collected based on the established PDU session for training the network model used by the mobile communication network.

[0086] In some optional embodiments, the user plane data collected for training the network model used by the mobile communication network may include at least one of the following: network parameters collected by access network elements, measurement data collected by location management function elements, and network parameters measured by user equipment.

[0087] In some alternative embodiments, the network parameters measured by the user equipment may include one or more of the following parameters: RSRP, RSRQ, SINR, RSSI, Cell-id, etc.

[0088] In some optional embodiments, the network parameters collected by the access network element may include one or more of the following parameters: RSRP, RSRQ, SINR, RSSI, and Cell-id. Depending on different application scenarios or requirements, they may also include more information about the wireless environment, such as frequency band usage and channel state information related to beamforming. Optionally, the network parameters collected by the access network element can be sent by the access network element to the session management function element through the AMF element, and then sent by the session management function element to the user equipment.

[0089] In some optional embodiments, the Location Management Function (LMF) network element is primarily responsible for handling management and functions related to user equipment positioning. The measurement data collected by the LMF network element can be positioning-related measurement data, such as TOA, AOA, Sounding Reference Signal (SRS) resource periods, and can also include Global Navigation Satellite System (GNSS) data, inter-base station time synchronization information, etc. This information helps improve the accuracy and reliability of positioning services. Optionally, the measurement data collected by the LMF network element can be sent by the LMF network element to the Session Management Function (AMF) network element, and then by the Session Management Function (AMF) network element to the user equipment.

[0090] In S430, user plane data is sent to the user plane function network element so that the user plane function network element can provide the user plane data to the target network element for network model training.

[0091] In some optional embodiments, the UE may send the user plane data used for training the network model to the UPF after collecting it. Alternatively, the UE may send the collected user plane data used for training the network model to the UPF only after receiving an instruction from a designated core network element (such as SMF, UPF, AMF, etc.).

[0092] In some optional embodiments, the UE can receive a transmission control configuration policy for the aforementioned user plane data sent by the session management function network element, and then send the user plane data used for training the network model to the UPF according to the transmission control configuration policy. This embodiment's technical solution allows the UE to adjust parameters such as the priority, bandwidth allocation, and routing path of the user plane data used for training the network model according to changes in real-time network conditions and service requirements. This ensures that the user plane data used for training the network model can be transmitted to the UPF in a timely and accurate manner even under network congestion, thus ensuring that the UPF can provide the target network element with the network model for training in a timely manner.

[0093] In some optional embodiments, the process of the UE sending user plane data to the user plane function network element can be as follows: First, the UE sends a data transmission request to the session management function network element. This data transmission request contains the UE's transmission control configuration policy. After receiving the data transmission request, if the session management function network element confirms that the transmission control configuration policy meets the requirements (e.g., it is consistent with the transmission control configuration policy sent to the UE by the session management function network element), then the session management function network element can send back confirmation information to the UE. Then, the UE can send the user plane data used for training the network model to the user plane function network element based on the transmission control configuration policy.

[0094] Optionally, if the session management function network element confirms that the transmission control configuration policy does not meet the requirements (e.g., it is inconsistent with the transmission control configuration policy sent to the UE by the session management function network element), then the session management function network element can send back a rejection message and an updated transmission control configuration policy to the UE. The UE can then send the user plane data used to train the network model to the user plane function network element based on the updated transmission control configuration policy.

[0095] In some optional embodiments, the user equipment can also report data transmission status information to core network elements (such as SMF network elements or other network elements), for example, periodically reporting data transmission status information, so that the core network elements can adjust the transmission control configuration strategy of user plane data according to the data transmission status information.

[0096] In summary, the technical solution of this application provides rich training samples for mobile communication networks by transmitting data through the user plane. This ensures that the trained network model can achieve more accurate traffic prediction, resource allocation, and fault diagnosis, thereby improving the intelligence and adaptability of the mobile communication network. Simultaneously, the technical solution of this application promotes the deep integration of AI and mobile communication technologies, driving the development of edge AI models in 5G-A / 6G network environments. This not only enhances the capabilities of existing networks but also paves the way for the development of more advanced network technologies in the future, greatly enhancing the functionality and flexibility of mobile communication networks.

[0097] The following section uses a 5G network as an example to further elaborate on the implementation details of the technical solution in the embodiments of this application:

[0098] In one embodiment of this application, the user plane data used during training of the network model (hereinafter referred to as the terminal model) required by the mobile communication network can be transmitted through the user plane data transmission process shown in FIG5. Specifically, referring to FIG5, the user plane data transmission process according to an embodiment of this application includes the following steps:

[0099] S501, the UE completes the initial access process, which may include selecting a PLMN, random access, authentication and encryption.

[0100] Optionally, the UE can scan for available network signals and select a PLMN based on preset priorities or user preferences. After selecting a PLMN, the UE will perform a random access procedure to establish an initial connection with the base station. This procedure includes sending a random access preamble, waiting for a response from the base station, and adjusting its transmission parameters according to the base station's instructions. Once random access is successful, the next step is authentication and encryption to ensure that only legitimate UEs can access network resources and to protect the security of user data.

[0101] Optionally, the authentication process typically involves the UE submitting authentication information to the network, such as the International Mobile Subscriber Identity (IMSI) or the Globally Unique Temporary UE Identity (GUTI), which the network then verifies through the Home Subscriber Server (HSS) or the Unified Data Management (UDM).

[0102] Optionally, the encryption process ensures that all communication between the UE and the network is encrypted, preventing sensitive information from being tampered with and ensuring the security and reliability of communication.

[0103] S502, the UE initiates a PDU session establishment request through the AMF and specifies the target data network, namely the OTT Server, as the server for training the end-side model.

[0104] Optionally, the PDU session establishment request sent by the UE may carry the network slice and QoS expected parameters required for edge model training, such as the latency, throughput, jitter, and other requirements for edge model training and data collection.

[0105] S503, SMF sends a request message to UPF, which may carry the transmission control configuration policy determined by PCF to instruct SMF to send user plane data streams related to edge model training based on the transmission control configuration policy.

[0106] Optionally, the transmission control configuration strategy determined by the PCF carried in the request information sent by the SMF to the UPF can allocate data stream priorities for the collection of edge model training data, thereby achieving dynamic bandwidth adjustment. When the amount of edge model training data surges, the UPF can automatically trigger a compression mechanism to optimize the compression transmission efficiency of the data transmission link.

[0107] S504, the UPF transmission control configuration strategy based on SMF, classifies and grades user plane data streams related to edge model training to facilitate flow control, such as controlling latency and bit rate, while distinguishing them from regular data traffic.

[0108] Alternatively, the UPF can classify and classify user plane data streams related to edge model training by assigning specific 5QIs, such as low-priority, high-reliability Non-GBR types, while regular traffic (such as video streams) may use high-bandwidth GBR types.

[0109] Optionally, the UPF can classify and classify traffic by using traffic inspection tools within the UPF. This involves labeling user plane data streams related to edge model training based on traffic characteristics and allocating different transmission bandwidths. Regular traffic, if real-time, is prioritized, while non-real-time traffic can be deferred. Alternatively, Deep Packet Inspection (DPI) technology can be used to parse specific fields (such as URL paths or parameters) in application layer protocols (such as HTTP / 2) of data packets to detect user plane data streams related to edge model training. Regular traffic, such as video streams or web page access, is generally transmitted via standard QoS streams and does not require additional parameter structure parsing.

[0110] Optionally, the UPF can establish a GPRS Tunneling Protocol-User plane (GTP-U) with the base station to facilitate the transmission of user plane data streams through the GTP-U tunnel. At the same time, the UPF can use the PDU session container field to define a standardized data format to transmit user plane data streams.

[0111] Alternatively, standardized data formats refer to uniform data types that conform to the 3GPP specifications, such as traffic statistics, application data transmission timestamps, QoS parameters, etc.

[0112] In S505, the RAN sends measurement parameters to the UE based on Radio Resource Control (RRC) commands. These parameters include, but are not limited to, Synchronization Signal Block (SSB) resource configuration information, Channel State Information Reference Signal (CSI-RS) resource configuration information, and RSRP reporting thresholds. The SSB is primarily used for cell search, synchronization, and initial access, forming the basis for the UE to establish a connection with the network. CSI-RS focuses on providing detailed channel state information to facilitate efficient resource allocation and link adaptation, enhancing overall network performance. The RSRP reporting threshold sets the conditions under which the UE should report its measurement results; for example, when the RSRP falls below a certain threshold, the UE needs to report this to the network.

[0113] Optionally, to ensure that different types of data are processed according to their quality of service requirements, the RAN can associate measurement data with specific QFIs. This helps to distinguish data streams of different priorities from other data collected by the UE side. For example, high-priority QFI=1 is used for real-time beam switching data, and low-priority QFI=2 is used for the collection of historical user plane data features.

[0114] In S506, the LMF sends the positioning reference signal measurement configuration to the gNB and UE via the Nlmf interface, including the SRS resource period and the measurement accuracy requirements for TOA and AoA. The SRS resource period specifies the time interval at which the UE sends SRS signals, which are used to evaluate uplink quality. The TOA and AoA measurement accuracy requirements define the accuracy standards for Time of Arrival (TOA) and Angle of Arrival (AoA) measurements; these parameters are crucial for achieving accurate location services.

[0115] Optionally, LMF can also ensure that collected location-related data is bound to a specific QFI to correctly classify and process this data in the network. For example, high-priority location data can be transmitted through streams with high QoS guarantees to ensure its real-time performance and accuracy. Simultaneously, LMF can also use different QFIs to distinguish user plane data streams collected for edge model training from other data, thereby optimizing resource utilization and quality of service.

[0116] S507, RAN and LMF will forward the collected data to SMF through AMF.

[0117] In S508, the SMF forwards the data collected by the RAN and LMF to the UE, while carrying the transmission control configuration policy determined by the SMF during the transmission process, such as bandwidth configuration information.

[0118] It should be noted that steps S505 to S508 shown in Figure 5 are optional. That is, the user plane data stream collected by the UE for edge model training may not include data collected by the RAN and LMF. In this case, the user plane data stream for edge model training can consist entirely of data collected by the UE itself. In other embodiments of this application, the user plane data stream for edge model training may also include data collected by the UE itself and data collected by the RAN; or it may include data collected by the UE itself and data collected by the LMF.

[0119] Meanwhile, if steps S505 to S508 shown in Figure 5 are optional, the SMF can also send transmission control configuration policies, such as bandwidth configuration information, to the UE separately, so that the UE can transmit user plane data streams for end-side model training based on the transmission control configuration policies.

[0120] S509, the OTT server sends a request message to the target network element in the core network. The request message is used to instruct the target network element to request the UE to provide user plane data for end-side model training. After that, the target network element can send an instruction to the UE to instruct the UE to send the user plane data for end-side model training through the user plane.

[0121] It should be noted that the target network element can be one network element, or two or more network elements. Optionally, the target network element can include at least the NEF network element. In this case, the OTT server can send a request message to the NEF network element, which can then forward the request message to the SMF or AMF. The AMF then instructs the UE to send user plane data for edge model training via the user plane. Alternatively, the SMF can instruct the UPF, which in turn sends a command to the UE via the user plane to instruct the UE to send user plane data for edge model training via the user plane.

[0122] In other embodiments of this application, the target network element may also be a newly defined network element that can receive request messages sent by the OTT server and then send instructions to the UE directly or through other network elements to instruct the UE to send user plane data for end-side model training through the user plane.

[0123] S510, the UE transmits the user plane data stream collected for edge model training (which may include one or more of the following information: Cell-id, RSRP, RSRQ, SINR, RSSI, index of UE-level network data and encapsulated standardized data, etc.) to the UPF.

[0124] Optionally, the user plane data streams collected by the UE side involve data of different classification and level. Different types of data can be configured with different transmission bandwidths according to the transmission control configuration policy obtained from the SMF, and then transmitted to the UPF.

[0125] Optionally, before transmitting the collected user plane data stream to the UPF, the UE can first send a data transmission request to the SMF to prompt the SMF to trigger the core network's collection and transmission management policy for the end-side model training data. This request can carry the transmission control configuration policy (such as bandwidth configuration rules, data encapsulation format, etc.) used by the UE before transmitting the collected user plane data stream. After receiving the request from the UE, the SMF can pause the dynamic bandwidth transmission configuration policy and determine whether the received transmission control configuration policy (such as bandwidth configuration rules, data encapsulation format, etc.) is consistent with the transmission control configuration policy previously sent to the UE. If they are consistent, the SMF replies to the UE with a confirmation message that transmission is permitted; if they are inconsistent, the SMF replies to the UE with a request to refuse transmission, carrying the latest dynamic configuration policy. After receiving the confirmation message from the SMF, the UE executes the user plane data stream transmission procedure; if it receives a request to refuse transmission, it updates the latest dynamic configuration policy before transmitting the user plane data stream.

[0126] S511, UPF encapsulates the user plane data stream sent by the UE for end-side model training. During the encapsulation process, QFI, RQI and encryption algorithms can be carried through the PDU session container.

[0127] S512, UPF transmits user plane data streams to target network elements through a specific secure link, so that the target network elements can perform training processing of the edge model.

[0128] It should be noted that in some embodiments of this application, the UE may also send the user plane data collected for edge model training to the UPF in advance. In this case, if the request message sent by the OTT server reaches the target network element, the target network element may send an indication message to the UPF to instruct the UPF to send the user plane data for edge model training to the OTT server.

[0129] In some embodiments of this application, the UE may not send the collected user plane data for edge model training to the UPF in advance. Instead, after the request message sent by the OTT server arrives at the target network element, the target network element sends an indication message to the UPF. In this case, the UPF may instruct the UE to send the collected user plane data for edge model training to the UPF, and then the UPF will send the user plane data for edge model training to the OTT server.

[0130] In step S513, during the execution of steps S501-S512 above, the AMF can monitor the status information of the UE's request to determine whether it is necessary to request the RAN and LMF to retransmit the network information on the base station side. Optionally, if the AMF detects an anomaly in the data (such as data sent by the RAN or LMF) (such as incorrect data format or incorrect data labeling), the AMF can send an error code to the LMF or RAN to trigger a process for retransmitting network measurement data.

[0131] In S514, throughout the entire process, the UE can periodically report the data transmission status (such as latency, throughput, etc.) to the core network. The SMF can then dynamically optimize the QoS policy configuration based on the UE's reported status. For example, the core network can dynamically adjust the data transmission strategy based on network conditions. When bandwidth congestion is detected, the PCF can issue a command through the SMF to force the UE to transmit only critical feature data for training the edge model. Optionally, for sensitive data requiring encryption, the UPF can append a security container to the GTP-U header and specify the encryption algorithm and key index.

[0132] S515, terminate the PDU session and end the transmission process of the user plane data stream.

[0133] In some optional embodiments, terminating the PDU session can be initiated by the UE, as shown in Figure 6, and includes the following steps:

[0134] S601, the UE sends a PDU session release request to the SMF.

[0135] Optionally, when the UE detects that the transmission link corresponding to the current PDU session is congested or that the transmission of user plane data has been completed, it may send a PDU session release request to the SMF.

[0136] S602, SMF sends a notification message to UPF to notify UPF to clear the GTP-U tunnel.

[0137] S603, the UPF sends a packet to the AMF to terminate the transmission request, the AMF updates the PDU session state in the UDM, and at the same time the RAN and LMF stop forwarding the beam information from the base station side to the UE.

[0138] Optionally, if the UE does not request to terminate the PDU session, but the UE remains inactive for a certain period of time, the UPF can trigger the release of the PDU session.

[0139] In some optional embodiments, terminating a PDU session can be initiated by the RAN, as shown in Figure 7, and includes the following steps:

[0140] S701, the RAN sends a PDU session termination request to the SMF via the RRC command.

[0141] Optionally, the RAN can send a PDU session termination request to the SMF network element if it detects transmission link congestion.

[0142] S702, SMF notifies UPF to send a notification message indicating that the PDU session has been terminated via N4 port.

[0143] After receiving the notification message that the PDU session has been terminated, the S703 UPF stops forwarding data and notifies the RAN to release radio resources.

[0144] In some optional embodiments, terminating a PDU session can be initiated by the PCF, as shown in Figure 8, and includes the following steps:

[0145] S801, the PCF sends a QoS update command to the SMF via the N7 interface for collecting training data for the edge model. Optionally, this QoS update command can be used to instruct the cessation of user plane data transmission.

[0146] S802, SMF sends QoS update command to UPF.

[0147] After receiving a QoS update instruction, if the QoS update instruction is used to indicate the cessation of user plane data transmission, the UPF will stop the forwarding of user plane data and notify the RAN to release radio resources.

[0148] The technical solutions of the above embodiments of this application propose a transmission process for user plane data used during training of the edge model, realizing standardized data transmission through the user plane for training of the edge model. This includes initiating, terminating, and managing the data transmission process of user equipment through the user plane connection, promoting the deep integration of AI technology and mobile communication technology, driving the development of edge AI models in 5G-A / 6G network environments, and enhancing the functionality and flexibility of mobile communication networks.

[0149] It should be noted that, in the embodiments of this application, the edge model can be trained on an OTT-server, on a core network element, or on other devices. After training is complete, the edge model can be deployed on a user device, an application server, or an access network element. Furthermore, the technical solutions of the embodiments of this application are not only applicable to 5G, 5G-A, and 6G mobile communication networks, but also to subsequently evolved mobile communication systems.

[0150] The following describes an apparatus embodiment of this application, which can be used to execute the data processing method described above in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the data processing method described above in this application.

[0151] Figure 9 shows a block diagram of a data processing apparatus according to an embodiment of the present application. The data processing apparatus can be applied to a UPF or other network elements.

[0152] Referring to FIG9, a data processing apparatus 900 according to an embodiment of the present application includes: an acquisition unit 902 and a transmission unit 904.

[0153] The acquisition unit 902 is configured to acquire user plane data sent by the user equipment, wherein the user plane data is used to train the network model used by the mobile communication network; the sending unit 904 is configured to send the user plane data to the target network element so that the target network element trains the network model based on the user plane data.

[0154] In some embodiments of this application, based on the foregoing scheme, the data processing device 900 further includes: a receiving unit configured to receive a transmission control configuration policy for the user plane data sent by the session management function network element; and a sending unit 904 configured to send the user plane data to the target network element according to the transmission control configuration policy.

[0155] In some embodiments of this application, based on the foregoing scheme, the sending unit 904 is configured to: allocate a quality of service identifier to the user plane data that is different from other data according to the transmission control configuration policy; and send the user plane data to the target network element based on the quality of service identifier allocated to the user plane data.

[0156] In some embodiments of this application, based on the foregoing scheme, the sending unit 904 is configured to: mark the user plane data in the data to be transmitted, allocate corresponding transmission resources to the user plane data according to the transmission control configuration policy, and use the allocated transmission resources to send the user plane data to the target network element.

[0157] In some embodiments of this application, based on the foregoing scheme, the sending unit 904 is configured to: encapsulate the user plane data through a Protocol Data Unit (PDU) session container, and add the quality of service control information corresponding to the user plane data to the PDU session container; and send the PDU session container containing the user plane data to the target network element.

[0158] In some embodiments of this application, based on the foregoing scheme, the data processing device 900 further includes: a receiving unit configured to receive indication information sent by a designated core network element, and send a request message to the user equipment based on the indication information to request the user equipment to send the user plane data.

[0159] In some embodiments of this application, based on the foregoing scheme, the sending unit 904 is configured to: receive indication information sent by a designated core network element for indicating the sending of the user plane data, and send the user plane data to the target network element according to the indication information.

[0160] In some embodiments of this application, based on the foregoing scheme, the sending unit 904 is configured to: when receiving the user plane data sent by the user equipment, send the user plane data to the target network element.

[0161] In some embodiments of this application, based on the foregoing scheme, the data processing device 900 further includes: a receiving unit configured to receive a notification message sent by the session management function network element, the notification message being used to indicate the termination of the PDU session of the user equipment;

[0162] The data processing apparatus 900 further includes: a processing unit configured to perform at least one of the following steps according to the notification message: notifying an access network element to release radio resources; sending a request message to an access and mobility management function (AM) element to cause the AM element to update the state of the PDU session; and stopping the forwarding of the user plane data.

[0163] In some embodiments of this application, based on the foregoing scheme, the notification message is sent by the session management function network element after receiving the PDU session release request sent by the user equipment; or

[0164] The notification message is sent by the session management function network element after receiving a PDU session termination request sent by the access network element via radio resource control signaling. The PDU session termination request is sent by the access network element to the session management function network element when radio resource congestion is detected; or

[0165] The notification message is sent by the session management function network element after receiving the quality of service update instruction sent by the policy control function network element. The quality of service update instruction is used to instruct the cessation of the transmission of the user plane data.

[0166] Figure 10 shows a block diagram of a data processing apparatus according to an embodiment of the present application, which can be applied to a UE or other devices.

[0167] Referring to FIG10, a data processing apparatus 1000 according to an embodiment of the present application includes: a processing unit 1002, a collection unit 1004, and a transmission unit 1006.

[0168] The processing unit 1002 is configured to initiate a PDU session establishment request to the access and mobility management function network element to establish a PDU session corresponding to the user equipment; the collection unit 1004 is configured to collect user plane data for training the network model used by the mobile communication network based on the PDU session; and the sending unit 1006 is configured to send the user plane data to the user plane function network element so that the user plane function network element provides the user plane data to the target network element for network model training.

[0169] In some embodiments of this application, based on the foregoing scheme, the user plane data collected for training the network model used by the mobile communication network includes at least one of the following data: network parameters collected by the access network element, measurement data collected by the location management function element, and network parameters measured by the user equipment.

[0170] The network parameters collected by the access network element are sent by the access network element to the session management function network element, and then sent by the session management function network element to the user equipment.

[0171] The measurement data collected by the positioning management function network element is sent by the positioning management function network element to the session management function network element, and then sent by the session management function network element to the user equipment.

[0172] In some embodiments of this application, based on the foregoing scheme, the data processing device 1000 further includes: a receiving unit configured to receive a transmission control configuration strategy for the user plane data sent by a session management function network element;

[0173] The sending unit 1006 is configured to send the user plane data to the user plane function network element according to the transmission control configuration strategy.

[0174] In some embodiments of this application, based on the foregoing scheme, the sending unit 1006 is configured to: send a data transmission request to a session management function network element, the data transmission request including a transmission control configuration policy; if a confirmation of transmission is received from the session management function network element, the user plane data is sent to the user plane function network element based on the transmission control configuration policy; wherein, the confirmation of transmission is fed back by the session management function network element after confirming that the transmission control configuration policy meets the requirements.

[0175] In some embodiments of this application, based on the foregoing scheme, the sending unit 1006 is configured to: if it receives a rejection message from the session management function network element and an updated transmission control configuration policy, then send the user plane data to the user plane function network element based on the updated transmission control configuration policy.

[0176] In some embodiments of this application, based on the foregoing scheme, the sending unit 1006 is further configured to: report data transmission status information to the core network element, so that the core network element adjusts the transmission control configuration strategy of the user plane data according to the data transmission status information.

[0177] Figure 11 shows a schematic diagram of the structure of a computer system suitable for implementing the computer device of the present application. The computer device may be a UPF or UE as described in the foregoing embodiments.

[0178] It should be noted that the computer system 1100 of the computer device shown in Figure 11 is only an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0179] As shown in Figure 11, the computer system 1100 may include a Central Processing Unit (CPU) 1101, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 1102 or programs loaded from storage portion 1108 into Random Access Memory (RAM) 1103, such as performing the methods described in the above embodiments. The RAM 1103 also stores various programs and data required for system operation. The CPU 1101, ROM 1102, and RAM 1103 are interconnected via a bus 1104. An Input / Output (I / O) interface 1105 is also connected to the bus 1104.

[0180] The following components can be connected to I / O interface 1105: an input section 1106 including a keyboard, mouse, etc.; an output section 1107 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 1108 including a hard disk, etc.; and a communication section 1109 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 1109 performs communication processing via a network such as the Internet. A drive 1110 is also connected to I / O interface 1105 as needed. Removable media 1111, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 1110 as needed so that computer programs read from them can be installed into storage section 1108 as needed.

[0181] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1109, and / or installed from removable medium 1111. When the computer program is executed by central processing unit (CPU) 1101, it performs various functions defined in the system of this application.

[0182] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a computer program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. The transmitted data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0183] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and a computer program.

[0184] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0185] In another aspect, this application also provides a computer-readable medium, which may be included in the computer device described in the above embodiments; or it may exist independently and not assembled into the computer device. The computer-readable medium carries one or more computer programs, which, when executed by the computer device, cause the computer device to perform the methods described in the above embodiments.

[0186] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0187] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, and includes several instructions to cause a computer device to execute the method according to the embodiments of this application.

[0188] For example, a computer device can be a UPF, in which case the UPF can execute the data processing method shown in Figure 3; another example is that a computer device can be a UE, in which case the UE can execute the data processing method shown in Figure 4.

[0189] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0190] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A data processing method, characterized in that, Applied to user plane function network elements, including: Acquire user plane data sent by the user equipment, the user plane data being used to train the network model used by the mobile communication network; The user plane data is sent to the target network element so that the target network element can train the network model based on the user plane data.

2. The data processing method according to claim 1, characterized in that, The data processing method further includes: receiving a transmission control configuration strategy for the user plane data sent by a session management function network element; Sending the user plane data to the target network element includes: sending the user plane data to the target network element according to the transmission control configuration policy.

3. The data processing method according to claim 2, characterized in that, According to the transmission control configuration policy, the user plane data is sent to the target network element, including: According to the transmission control configuration policy, a quality of service identifier that is different from other data is assigned to the user plane data; Based on the quality of service identifier assigned to the user plane data, the user plane data is sent to the target network element.

4. The data processing method according to claim 2, characterized in that, According to the transmission control configuration policy, the user plane data is sent to the target network element, including: Mark the user plane data in the data to be transmitted, and allocate corresponding transmission resources to the user plane data according to the transmission control configuration policy; The user plane data is sent to the target network element using the allocated transmission resources.

5. The data processing method according to claim 1, characterized in that, Sending the user plane data to the target network element includes: The user plane data is encapsulated and processed by the Protocol Data Unit (PDU) session container, and the service quality control information corresponding to the user plane data is added to the PDU session container. The PDU session container encapsulating the user plane data is sent to the target network element.

6. The data processing method according to claim 1, characterized in that, The data processing method further includes: receiving indication information sent by a designated core network element, and sending a request message to the user equipment based on the indication information to request the user equipment to send the user plane data; or Sending the user plane data to the target network element includes: receiving an instruction message sent by a designated core network element to instruct the sending of the user plane data, and sending the user plane data to the target network element according to the instruction message; or sending the user plane data to the target network element when the user equipment sends the user plane data.

7. The data processing method according to any one of claims 1 to 6, characterized in that, The data processing method further includes: Receive a notification message sent by the session management function network element, the notification message being used to indicate the termination of the PDU session of the user equipment; Perform at least one of the following steps according to the notification message: notify the access network element to release radio resources; send a request message to the access and mobility management function element to update the state of the PDU session; and stop forwarding the user plane data.

8. The data processing method according to claim 7, characterized in that, The notification message is sent by the session management function network element after receiving the PDU session release request sent by the user equipment; or The notification message is sent by the session management function network element after receiving a PDU session termination request sent by the access network element via radio resource control signaling. The PDU session termination request is sent by the access network element to the session management function network element when radio resource congestion is detected; or The notification message is sent by the session management function network element after receiving the quality of service update instruction sent by the policy control function network element. The quality of service update instruction is used to instruct the cessation of the transmission of the user plane data.

9. A data processing method, characterized in that, Applied to user equipment, including: Initiate a Protocol Data Unit (PDU) session establishment request to the Access and Mobility Management Function (AMS) network element to establish a PDU session corresponding to the user equipment; Based on the PDU session, user plane data is collected for training the network model used by the mobile communication network; The user plane data is sent to the user plane function network element, so that the user plane function network element provides the user plane data to the target network element for network model training.

10. The data processing method according to claim 9, characterized in that, The user plane data collected for training the network model used by the mobile communication network includes at least one of the following: network parameters collected by access network elements, measurement data collected by location management function elements, and network parameters measured by user equipment. The network parameters collected by the access network element are sent by the access network element to the session management function network element, and then sent by the session management function network element to the user equipment. The measurement data collected by the positioning management function network element is sent by the positioning management function network element to the session management function network element, and then sent by the session management function network element to the user equipment.

11. The data processing method according to claim 9, characterized in that, The data processing method further includes: receiving a transmission control configuration strategy for the user plane data sent by a session management function network element; Sending the user plane data to the user plane function network element includes: sending the user plane data to the user plane function network element according to the transmission control configuration policy.

12. The data processing method according to claim 9, characterized in that, Sending the user plane data to the user plane function network element includes: Send a data transmission request to the session management function network element, wherein the data transmission request contains a transmission control configuration policy; If the session management function network element receives a confirmation message, the user plane data is sent to the user plane function network element based on the transmission control configuration policy; wherein, the confirmation message is sent by the session management function network element after confirming that the transmission control configuration policy meets the requirements.

13. The data processing method according to claim 12, characterized in that, The data processing method further includes: If a rejection message is received from the session management function network element, along with an updated transmission control configuration policy, the user plane data is sent to the user plane function network element based on the updated transmission control configuration policy.

14. The data processing method according to any one of claims 9 to 13, characterized in that, The data processing method further includes: The data transmission status information is reported to the core network elements so that the core network elements can adjust the transmission control configuration strategy of the user plane data according to the data transmission status information.

15. A data processing apparatus, characterized in that, Configured in user plane functional network elements, including: The acquisition unit is configured to acquire user plane data sent by the user equipment, wherein the user plane data is used to train the network model used by the mobile communication network; The sending unit is configured to send the user plane data to the target network element so that the target network element can train the network model based on the user plane data.

16. A data processing apparatus, characterized in that, Configured in user equipment, including: The processing unit is configured to initiate a Protocol Data Unit (PDU) session establishment request to the access and mobility management function network element in order to establish a PDU session corresponding to the user equipment. The collection unit is configured to collect user plane data for training the network model used by the mobile communication network based on the PDU session; The sending unit is configured to send the user plane data to the user plane function network element, so that the user plane function network element provides the user plane data to the target network element for network model training.

17. A data processing system, characterized in that, include: User plane function network element, wherein the user plane function network element is used to execute the data processing method according to any one of claims 1 to 8; as well as, User equipment, the user equipment being used to perform the data processing method according to any one of claims 9 to 14.

18. A computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the data processing method according to any one of claims 1 to 14.

19. A computer device, characterized in that, include: One or more processors; A memory for storing one or more computer programs, which, when executed by the one or more processors, cause the computer device to perform the data processing method according to any one of claims 1 to 14.

20. A computer program product, characterized in that, The computer program product includes a computer program stored in a computer-readable storage medium, wherein a processor of a computer device reads from the computer-readable storage medium and executes the computer program, causing the computer device to perform the data processing method according to any one of claims 1 to 14.