Pdu session management method, device, system, electronic device and storage medium

Abstract

The present disclosure provides a PDU session management method, device, system, electronic equipment and storage medium, wherein the PDU session management method comprises: receiving subscription data of a terminal device sent by a unified data management function (UDM) entity, wherein the subscription data contains operation parameters, and the operation parameters are used to obtain task information of an artificial intelligence (AI) task and / or a machine learning (ML) task executed on the terminal device; obtaining a network data analysis result of the terminal device from a network data analysis function (NWDAF) entity; and activating or releasing a PDU session in which the AI task and / or the ML task of the terminal device is executed based on the operation parameters and the network data analysis result. By writing the operation parameters of the AI task and / or the ML task into the subscription data, the SMF entity manages the PDU session in which the AI task and / or the ML task of the terminal device is executed according to the operation parameters and the network data analysis result of the NWDAF entity on the terminal device, thereby improving the data privacy of the terminal device and the network resource utilization efficiency.

Description

Technical Field

[0001] This disclosure relates to the field of wireless communication technology, and in particular to a PDU session management method, apparatus, system, electronic device, and storage medium. Background Technology

[0002] As AI (Artificial Intelligence) or ML (Arthur Samuel) tasks become increasingly common, the limited memory and computing power of terminal devices prevent them from performing heavyweight AI or ML tasks. Currently, the common practice is to upload data from the terminal device to a cloud server, train and infer models on the cloud server, and then return the results to the terminal device.

[0003] Existing technologies, given the characteristics of AI or ML tasks—large data transmission volumes, potential iterative processes, high latency requirements, and the need for UE (User Equipment) or third parties to adjust transmission tasks in real time based on network conditions—necessary network state change information or predictions from the 5GC (5G Core) needs to be exposed to the UE or third-party servers to ensure that AI or ML tasks do not excessively consume network resources and affect other services. This allows the UE or third-party servers to determine the splitting points for AI or ML tasks, the timing of model and data transmission, etc. Currently, many terminal manufacturers have proposed solutions that directly expose network data such as physical load and network performance to the UE or third parties. However, directly exposing network data to the UE or third parties involves numerous security risks.

[0004] Therefore, how to solve the problem of excessive network resource consumption and network data leakage risks caused by PDU (Protocol Data Unit) sessions executing AI or ML tasks on terminal devices has become an urgent issue to be addressed.

[0005] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] This disclosure provides a PDU session management method, apparatus, system, electronic device, and storage medium, which at least to some extent overcomes the problems in related technologies where PDU sessions executing AI or ML tasks on terminal devices excessively consume network resources and pose a risk of network data leakage.

[0007] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part by practice of this disclosure.

[0008] According to one aspect of this disclosure, a Protocol Data Unit (PDU) session management method is provided, applied to a Session Management Function (SMF) entity, comprising: receiving subscription data of a terminal device sent by a Unified Data Management (UDM) entity, wherein the subscription data includes operation parameters, the operation parameters being used to obtain task information of an artificial intelligence (AI) task and / or a machine learning (ML) task executed on the terminal device; obtaining network data analysis results of the terminal device from a Network Data Analysis Function (NWDAF) entity; and activating or releasing the PDU session of the terminal device executing the AI ​​task and / or ML task based on the operation parameters and the network data analysis results.

[0009] In one embodiment of this disclosure, the operation parameters are written by the Application Function (AF) entity to the subscription data of the terminal device stored on the UDM entity through the Network Exposure Function (NEF) entity.

[0010] In one embodiment of this disclosure, the method further includes obtaining network data analysis results of the terminal device from a Network Data Analysis Function (NWDAF) entity, wherein the network data analysis request is used to request the NWDAF entity to analyze the network resource utilization and / or terminal status of the terminal device; and receiving the network data analysis results of the terminal device returned by the NWDAF entity.

[0011] In one embodiment of this disclosure, receiving data analysis results sent by the Network Data Analysis Function (NWDAF) entity includes: receiving network data analysis results returned by the NWDAF entity within a preset time period.

[0012] In one embodiment of this disclosure, the preset duration is the effective duration of the AI ​​task and / or the effective duration of the ML task. Receiving network data analysis results returned by the NWDAF entity within the preset duration includes: receiving network data analysis results sent by the NWDAF entity within the effective duration of the AI ​​task and / or the effective duration of the ML task.

[0013] In one embodiment of this disclosure, the data analysis results include the network resource utilization and / or terminal status of the terminal device; based on the operation parameters and the network data analysis results, activating or releasing the PDU session for the terminal device to perform AI tasks and / or ML tasks includes: activating or releasing the PDU session for the terminal device to perform AI tasks and / or ML tasks based on the operation parameters, network resource utilization and terminal status.

[0014] According to another aspect of this disclosure, a Protocol Data Unit (PDU) session management device is provided, applied to the Session Management Function (SMF) entity side. The device includes: a subscription data receiving module, used to receive subscription data of a terminal device sent by a Unified Data Management Function (UDM) entity, wherein the subscription data includes operation parameters, the operation parameters being used to obtain task information of artificial intelligence (AI) tasks and / or machine learning (ML) tasks executed on the terminal device; an analysis result acquisition module, used to obtain network data analysis results of the terminal device from a Network Data Analysis Function (NWDAF) entity; and a PDU session management module, used to activate or release the PDU session of the terminal device executing AI tasks and / or ML tasks based on the operation parameters and the network data analysis results.

[0015] In one embodiment of this disclosure, the analysis result acquisition module is further configured to send a network data analysis request to the NWDAF entity, wherein the network data analysis request is used to request the NWDAF entity to analyze the network resource utilization and / or terminal status of the terminal device; and to receive the network data analysis results of the terminal device returned by the NWDAF entity.

[0016] In one embodiment of this disclosure, the analysis result acquisition module is further configured to receive network data analysis results returned by the NWDAF entity within a preset time period.

[0017] In one embodiment of this disclosure, the preset duration is the effective duration of the AI ​​task and / or the effective duration of the ML task. The analysis result acquisition module is further configured to receive network data analysis results sent by the NWDAF entity within the effective duration of the AI ​​task and / or the effective duration of the ML task.

[0018] In one embodiment of this disclosure, the data analysis results include the network resource utilization and / or terminal status of the terminal device. The PDU session management module is further configured to activate or release the PDU session of the terminal device performing AI tasks and / or ML tasks based on the operation parameters, network resource utilization and terminal status.

[0019] According to another aspect of this disclosure, a Protocol Data Unit (PDU) session management system is provided, comprising a Session Management Function (SMF) entity, a Network Data Analysis Function (NWDAF) entity, a Unified Data Management (UDM) entity, and a terminal device. The UDM entity sends subscription data from the terminal device to the SMF entity. The Application Function (AF) entity, through a Network Open Function (NEF) entity, writes operation parameters of AI and / or ML tasks executed on the terminal device into the subscription data stored on the UDM entity. The subscription data includes operation parameters used to obtain task information for the AI ​​and / or ML tasks executed on the terminal device. The NWDAF entity receives network data analysis requests from the SMF entity and returns network data analysis results to the SMF entity. The network data analysis requests request the NWDAF entity to analyze the network resource utilization and / or terminal status of the terminal device. The SMF entity receives the subscription data and the network data analysis results, and, based on the operation parameters and the network data analysis results, activates or releases the PDU session executing the AI ​​and / or ML tasks on the terminal device.

[0020] According to another aspect of this disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the above-described Protocol Data Unit (PDU) session management method by executing the executable instructions.

[0021] According to another aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the above-described Protocol Data Unit (PDU) session management method.

[0022] This disclosure provides a PDU session management method, apparatus, system, electronic device, and storage medium. The PDU session management method includes: receiving subscription data from a terminal device sent by a Unified Data Management Function (UDM) entity, wherein the subscription data includes operation parameters used to obtain task information of artificial intelligence (AI) tasks and / or machine learning (ML) tasks executed on the terminal device; obtaining network data analysis results from a Network Data Analysis Function (NWDAF) entity; and activating or releasing the PDU session for the terminal device executing AI and / or ML tasks based on the operation parameters and the network data analysis results. This disclosure improves data privacy and network resource utilization efficiency of the terminal device by writing the operation parameters of AI and / or ML tasks into the subscription data, allowing the SMF entity to manage the PDU session for the terminal device executing AI and / or ML tasks based on the operation parameters and the network data analysis results of the NWDAF entity.

[0023] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0024] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0025] Figure 1 This diagram illustrates a communication network system architecture according to an embodiment of the present disclosure;

[0026] Figure 2 This diagram illustrates a flowchart of a PDU session management method according to an embodiment of the present disclosure;

[0027] Figure 3 This diagram illustrates a PDU session management method according to an embodiment of the present disclosure.

[0028] Figure 4 This diagram illustrates another PDU session management method according to an embodiment of the present disclosure.

[0029] Figure 5 This diagram illustrates another PDU session management method in an embodiment of the present disclosure.

[0030] Figure 6 This diagram illustrates a PDU session management device according to an embodiment of the present disclosure.

[0031] Figure 7 This diagram illustrates a PDU session management system according to an embodiment of the present disclosure; and

[0032] Figure 8 A structural block diagram of an electronic device according to an embodiment of the present disclosure is shown. Detailed Implementation

[0033] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that this disclosure will be more comprehensive and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0034] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may 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.

[0035] As mentioned in the background section, the number of AI or ML applications has been increasing in recent years. Due to the limited memory and computing power of terminal devices, they cannot complete heavyweight AI or ML tasks. Currently, the common practice is to upload data from the terminal device to a cloud server, where model training and inference are performed, and the results are returned to the terminal device. However, this approach places enormous computational and storage pressure on cloud servers, exposes user information, and fails to meet the low-latency business requirements of applications such as VR (Virtual Reality), AR (Augmented Reality), or autonomous driving. Therefore, federated learning and distributed learning first break down an AI or ML task. One part, involving user privacy, is performed on the terminal side, with intermediate data or models transmitted to the network side. The other part, requiring significant computing power and energy, is performed on the network side. This approach ensures user privacy while reducing the computational demands on devices.

[0036] Currently, 3GPP (3rd Generation Partnership Project) SA2's Release 18 (R18) for AI or ML has proposed three new requirements for 5G (5th Generation Mobile Communication Technology)+ networks to ensure the smooth execution of AI or ML tasks: 1) task splitting; 2) distribution and sharing of AI or ML task models and data on the 5GS; and 3) support for application-layer federated learning or distributed learning. Furthermore, given the characteristics of AI or ML tasks—large data transmission volumes, potential iterative processes, high latency requirements, and the need for UEs or third parties to adjust transmission tasks in real-time based on network conditions—to ensure that AI or ML tasks do not excessively consume network resources and affect other network services, the 5GC needs to expose necessary network state change information or predictions to the UE or third-party servers. This allows the UE or third-party servers to determine the task splitting point, model execution, data transmission time or size, etc. Currently, many terminal manufacturers have proposed solutions that directly expose network data such as network element load and network performance to the UE or third parties. However, directly exposing network data to UEs or third parties involves many security risks.

[0037] Based on this, this disclosure provides a PDU session management method, apparatus, system, electronic device, and storage medium. By writing the operation parameters of AI tasks and / or ML tasks into the subscription data, the network data of the terminal device is not exposed to the server. The SMF entity then manages the PDU sessions of the terminal device executing AI tasks and / or ML tasks based on the operation parameters and the network data analysis results of the NWDAF entity. This avoids excessive occupation of the terminal device's network resources by the PDU sessions of AI tasks and / or ML tasks, thereby improving the data privacy and network resource utilization efficiency of the terminal device.

[0038] The technical solutions of this disclosure can be applied to various communication systems, such as: Global System of Mobile communication (GSM) system, Code Division Multiple Access (CDMA) system, Wideband Code Division Multiple Access (WCDMA) system, General Packet Radio Service (GPRS), Long Term Evolution (LTE) system, LTE Frequency Division Duplex (FDD) system, LTE Time Division Duplex (TDD) system, Universal Mobile Telecommunication System (UMTS), Worldwide Interoperability for Microwave Access (WIMAX) communication system, fifth-generation mobile communication technology system, or New Radio (NR), etc.

[0039] Figure 1 A schematic diagram of the structure of a communication network system that can be applied to embodiments of this disclosure is shown.

[0040] like Figure 1 As shown, the system may include NWDAF entity 110, UE entity 120, AMF entity 130, SMF entity 140, UDM entity 150, NEF entity 160 and AF entity 170.

[0041] Optionally, the system may further include one or more of the following: a Network Repository Function (NRF) entity, an Authentication Server Function (AUSF) entity, a Policy Control Function (PCF) entity, and a Data Network (DN).

[0042] NWDAF entity 110 is responsible for collecting data from various entities and analyzing the collected data to obtain data analysis results. The Nnwdaf (NF) service provides specific information services to the NWDAF entity. The NF service includes two services: Nnwdaf_EventsSubscription and Nnwdaf_AnalyticsInfo. The Nnwdaf_EventsSubscription service allows NF service users to subscribe to or unsubscribe from notifications of different analysis information from the NWDAF entity. The Nnwdaf_AnalyticsInfo service allows Nnwdaf service users to request and obtain specific analyses from the NWDAF entity.

[0043] The Nnwdaf_EventsSubscription service includes the following types: Slice load level information; Service experience; NF load; Network performance; Abnormal behavior; UE mobility; UE communication; User data congestion; and QoS sustainability. Structurally, NWDAF entities can connect to all other entities.

[0044] The service operations are as follows: The NF service uses the Nnwdaf_EventsSubscription_Subscribe service operation to subscribe to or update event notifications for analytics information. It can subscribe to periodic notifications or event detection notifications. The NF service uses the Nnwdaf_EventsSubscription_UnSubscribe service operation to unsubscribe from event notifications. The NWDAF entity uses the Nnwdaf_EventsSubscription_Notify service operation to notify NF service users of subscribed events. The application feature exposed service Naf_EventExposure is part of the interface exposed by the AF entity based on the Naf service. The known Nnwdaf service users of the Naf_EventExposure service are the NEF entity and the NWDAF entity.

[0045] UE Entity 120: This can be a terminal device, which may include various handheld devices, vehicle-mounted devices, wearable devices, computing devices, or other processing devices connected to a wireless modem with wireless communication capabilities; it may also include a subscriber unit, cellular phone, smartphone, wireless data card, personal digital assistant (PDA) computer, tablet computer, wireless modem, handheld device, laptop computer, cordless phone, wireless local loop (WLL) station, machine type communication (MTC) terminal, user equipment, mobile station (MS), terminal device, or relay user equipment, etc. Relay user equipment may be, for example, a 5G residential gateway (RG). For ease of description, the devices mentioned above are collectively referred to as terminal devices in this disclosure.

[0046] AMF Entity 130: Responsible for access and mobility management, with functions such as user authentication, handover, and location updates.

[0047] SMF Entity 140: Responsible for session management, including the establishment, modification, and release of packet data unit (PDU) sessions.

[0048] UDM Entity 150 can support the following functions: generation of authentication credentials for the Third Generation Partnership Project Authentication and Key Agreement (3GPPAKA); user identification processing, such as the storage and management of each user's SUPI (Subscription Permanent Identifier) ​​in a 5G system; support for unhiding the privacy-protected user identifier (SUCI); access authentication based on subscription data, such as roaming restrictions; NF registration management for UE services, such as storing AMF for UE services and SMF for UE PDU session services; support for service or session continuity by maintaining ongoing session allocation via SMF or DNN; MT-SMS delivery support; lawful interception functionality; subscription management; SMS management, etc.

[0049] NEF Entity 160: Supports the exposure of network capabilities. The exposed service capabilities mainly include monitoring, provisioning, policy / billing, and analytics reporting. In addition, the NEF entity can provide open security services to third-party applications. In 5G networks, the NEF entity is based on a service-oriented architecture and connects to all NF entities via a bus, exposing network capabilities to third-party applications. This enables seamless integration of network capabilities with service requirements, improves service experience, and optimizes network resource allocation.

[0050] AF Entity 170: A functional element that provides service or application-related information to NF service users. AF allows NF service users to subscribe to and unsubscribe from periodic notifications or notifications related to the detection of subscription events.

[0051] PCF entity: Responsible for user policy management, including both mobility-related policies and PDU session-related policies, such as quality of service (QoS) policies and billing policies.

[0052] UPF Entity: UPF stands for User Plane Function, which is responsible for forwarding user data.

[0053] DN: The destination of the user's PDU session access.

[0054] The following detailed description of this exemplary implementation method is provided in conjunction with the accompanying drawings and embodiments.

[0055] First, this disclosure provides a PDU session management method, which can be applied to an SMF entity, or can be executed by any electronic device with computing capabilities.

[0056] Figure 2 This diagram illustrates a flowchart of a PDU session management method according to an embodiment of the present disclosure, such as... Figure 1 As shown, the PDU session management method provided in this embodiment includes the following steps:

[0057] S202, Receive subscription data of terminal device sent by Unified Data Management (UDM) entity, wherein the subscription data includes operation parameters, which are used to obtain task information of artificial intelligence (AI) tasks and / or machine learning (ML) tasks executed on the terminal device.

[0058] In this step, the signing data contains the necessary information provided by the terminal device for signing. In addition, the signing data in this disclosure also carries operation parameters, which can be used to obtain the task information of the AI ​​task or ML task executed on the terminal device. The operation parameters may include AI task identifier, ML task identifier, AI task duration, ML task duration, AI task validity period or ML task validity period.

[0059] It should be noted that after the UE (User Equipment) establishes a PDU session to perform AI and / or ML tasks, it indicates that the session type is AI and / or ML task execution. The SMF (Service Management Provider) entity records the AI ​​and / or ML task execution type of the PDU session in the session management context. The SMF entity downloads the subscription data from the UDM (User Data Management Provider) entity and subscribes to changes in the subscription data. If the data in the UDM entity changes, it will call the callback URI (Uniform Resource Identifier) ​​sent when the SMF entity subscribed to notify the SMF entity. The HTTP (Hypertext Transfer Protocol) method for the SMF entity to download the subscription data is: front-end GET method to download the file, and the resource URI called is {apiRoot} / nudm-sdm / <apiversion> / supi / sm-data.

[0060] S204, obtaining a network data analysis result of the terminal device from a network data analysis function (NWDAF) entity.

[0061] It should be noted that the network data analysis result can include network resource utilization and terminal state of the terminal device, and the network resource utilization is a key parameter for measuring how much a network bandwidth is occupied and network congestion. If the network resource utilization is too high, it indicates that the network load of the terminal device is large. If the network resource utilization is low, it indicates that the network of the terminal device is idle. The NWDAF entity first obtains network data of the terminal device, and then analyzes the network data of the terminal device to obtain the network data analysis result of the terminal device.

[0062] S206, activating or releasing the PDU session for executing the AI task and / or the ML task of the terminal device based on the operation parameter and the network data analysis result.

[0063] In this step, whether to activate or release the PDU session for executing the AI task and / or the ML task of the terminal device can be determined according to the network data analysis result, and the PDU session for executing the AI task and / or the ML task is selected to be activated or released according to the operation parameter. For example, when the network data analysis result indicates that the network of the terminal device is in an idle state, it is determined to activate the PDU session for executing the AI task and / or the ML task. When the network data analysis result indicates that the network of the terminal device is in a busy state, it is determined to release the PDU session for executing the AI task and / or the ML task.

[0064] The PDU session management method provided by the embodiment of the present disclosure includes: receiving subscription data of a terminal device sent by a unified data management function (UDM) entity, wherein the subscription data contains an operation parameter, and the operation parameter is used to obtain task information of an artificial intelligence (AI) task and / or a machine learning (ML) task executed on the terminal device; obtaining a network data analysis result of the terminal device from a network data analysis function (NWDAF) entity; and activating or releasing a PDU session for executing the AI task and / or the ML task of the terminal device based on the operation parameter and the network data analysis result. By writing the operation parameter of the AI task and / or the ML task into the subscription data, the SMF entity manages the PDU session for executing the AI task and / or the ML task of the terminal device according to the operation parameter and the network data analysis result of the terminal device by the NWDAF entity, thereby improving the data privacy and network resource utilization efficiency of the terminal device.

[0065] In one embodiment of this disclosure, the operation parameters are written by the Application Function (AF) entity to the subscription data of the terminal device stored on the UDM entity through the Network Open Function (NEF) entity. To provide the terminal device with services for performing AI and / or ML tasks, it is necessary to obtain the user's task requirements for AI and / or ML tasks in real time. These task requirements may include the transmission duration of the model or raw data, the total length of data transmission, or the time requirement for each training round, etc. That is, the terminal device or third-party application server needs to expose the task information of the AI ​​and / or ML tasks to the network in real time so that the network can provide services for the AI ​​and / or ML tasks that the terminal device needs to perform based on the network resource usage of the terminal device. Generally, the group of UEs performing distributed learning or federated learning is selected by a third-party server based on relevant UE data, and the selected group of UEs participates in distributed learning or federated learning. After the UE establishes a PDU session for the AI ​​and / or ML tasks, it can report the task information of the AI ​​and / or ML tasks it needs to perform to the network in real time through the AF entity. The AF entity exposes the task information of the AI ​​or ML tasks to the UDM entity through the NEF entity. This task information may include parameters such as task identifier, duration, or effective time point.

[0066] See Figure 3 The diagram illustrates a PDU session management method. This disclosure enhances the existing External Parameter Provisioning (clause 4.15.6 in TS 23.502) function in the current standard, enabling the AF entity to register the task information of AI tasks and / or ML tasks in the UE subscription data that can and is capable of performing AI tasks and / or ML tasks through the NEF entity. The information can be updated in real time according to task requirements and operator configuration conditions. The task information of AI tasks and / or ML tasks may include AI task identifier, ML task identifier, AI task duration, ML task duration, AI task validity time, or ML task validity time.

[0067] This disclosure first utilizes the external data capabilities of the AF and NEF entities to enable the network to obtain real-time information about user demands for AI or ML tasks. Then, through the network intelligence function of the NWDAF entity, it obtains information about the network status and capabilities of terminal devices. After comprehensively considering the AI ​​task or ML service demands and the actual network resource usage, the network dynamically deactivates and activates PDU sessions. This disclosure helps operator networks grasp relevant information about AI or ML tasks, allocate appropriate transmission time for such services, and ensure that these services can proceed without affecting other services and users, thus fully guaranteeing the experience of all users. This disclosure utilizes the network intelligence function of the NWDAF entity to manage and control network resources of terminal devices without manual configuration, achieving the guarantee of various types of services.

[0068] See Figure 3 Table 1 lists the interfaces and parameters that need to be enhanced, as shown below:

[0069] Table 1

[0070]

[0071] In one embodiment of this disclosure, it can be achieved through Figure 4 The steps disclosed herein implement obtaining network data analysis results of terminal devices from the Network Data Analysis Function (NWDAF) entity. See [link to documentation]. Figure 4 Another publicly available flowchart for PDU session management may include the following steps:

[0072] S402, Send a network data analysis request to the NWDAF entity, wherein the network data analysis request is used to request the NWDAF entity to analyze the network resource utilization and / or terminal status of the terminal device.

[0073] It should be noted that network data analysis requests may include data information of target services subscribed by the SMF entity to the NWDAF entity, wherein the target service may be at least one or more of the following: Slice load level information, Service experience, NF load, Network performance, Abnormal behavior, UE mobility, UE communication, User data congestion, and QoS sustainability; the SMF entity may subscribe to and / or request the NWDAF entity to analyze target data of the terminal device, wherein the target data may be data characterizing the network status and / or terminal status of the terminal device. The network data analysis request may also include the operation parameters of the AI ​​task and / or ML task, the return conditions of the network data analysis results, or the target analysis time. The operation parameters of the AI ​​task and / or ML task may include the effective duration of the AI ​​task and / or ML task. The target analysis time may be less than or equal to the effective duration of the AI ​​task and / or ML task. The return conditions of the network data analysis results may be a preset time period, time threshold, or time cycle. The NWDAF entity may return the network data analysis results to the SMF entity within the preset time period, or the NWDAF entity may return the network data analysis results to the SMF entity when the time is higher or lower than the time threshold, or the NWDAF entity may periodically return the network data analysis results to the SMF entity.

[0074] S404: Receive network data analysis results from the NWDAF entity for the terminal device.

[0075] In this step, if the NWDAF entity satisfies the condition of returning network data analysis results, the SMF entity receives the network data analysis results of the terminal device returned by the NWDAF entity.

[0076] In one embodiment of this disclosure, receiving data analysis results sent by the Network Data Analysis Function (NWDAF) entity includes: receiving network data analysis results returned by the NWDAF entity within a preset time period.

[0077] In one embodiment of this disclosure, the preset duration is the effective duration of the AI ​​task and / or the effective duration of the ML task. Receiving network data analysis results returned by the NWDAF entity within the preset duration includes: receiving network data analysis results sent by the NWDAF entity within the effective duration of the AI ​​task and / or the effective duration of the ML task.

[0078] In one embodiment of this disclosure, the data analysis results include the network resource utilization and / or terminal status of the terminal device; based on the operation parameters and network data analysis results, the PDU session for the terminal device to perform AI tasks and / or ML tasks is activated or released, including: based on the operation parameters, network resource utilization and terminal status, the PDU session for the terminal device to perform AI tasks and / or ML tasks is activated or released.

[0079] It should be noted that network resource utilization can refer to the network resource utilization rate of the terminal device, and the terminal state can include idle and non-idle states. When the network resource utilization rate of the terminal device is low and / or the terminal state is idle, a PDU session for executing AI and / or ML tasks is activated according to the operation parameters; when the network resource utilization rate of the terminal device is high and / or the terminal state is non-idle, the PDU session for executing AI and / or ML tasks is released according to the operation parameters. Here, a network resource utilization threshold can also be set. The current network resource utilization level of the terminal device is determined by comparing the terminal device's network resource utilization rate with this threshold. For example, if the terminal device's network resource utilization rate is less than or equal to the threshold, it indicates that the terminal device's network resource utilization rate is low, and in this case, a PDU session for executing AI and / or ML tasks can be activated according to the operation parameters; if the terminal device's network resource utilization rate is greater than the threshold, it indicates that the terminal device's network resource utilization rate is high, and in this case, a PDU session for executing AI and / or ML tasks can be released according to the operation parameters. This disclosure allows for flexible management of PDU sessions by selecting to activate or release PDU sessions for AI and / or ML tasks on the terminal device based on the terminal device's network resource utilization and terminal status, and by using operational parameters. This ensures that AI and / or ML tasks do not excessively consume the terminal device's network resources, thereby improving the user's service experience and the terminal device's network resource utilization efficiency.

[0080] This disclosure describes a process where, when an SMF entity deactivates an AI task and / or ML task, the SMF entity triggers a PDU session deactivation procedure for the AI ​​task and / or ML task. This releases user-plane resources to ensure the experience of other tasks and the smooth operation of other user tasks.

[0081] In one embodiment of this disclosure, the SMF entity can trigger a service request process from the network side to reactivate the PDU session for executing AI and / or ML tasks on the terminal device. The SMF entity can choose to activate or deactivate the PDU session for executing AI and / or ML tasks based on the network resource usage and terminal status of the terminal device.

[0082] In one embodiment of this disclosure, see Figure 5 Another PDU session management method diagram is shown below, such as Figure 5 As shown, this other PDU session management method includes:

[0083] S502, Establish PDU session;

[0084] In this step, the UE entity initiates the process of establishing a PDU session to perform AI tasks and / or ML tasks, and indicates that the PDU session type is AI task type and / or ML task type.

[0085] S504, Acquisition of Contract Data;

[0086] In this step, the SMF entity retrieves the subscription data from the UDM entity and subscribes to changes in the subscription data. If the data in the UDM entity changes, it will call the callback URI sent when the SMF entity subscribed to notify the SMF entity. The subscription data carries operation parameters for AI tasks and / or ML tasks, which are used to obtain task information for the AI ​​tasks and / or ML tasks.

[0087] S506, send a network data analysis request;

[0088] In this step, the SMF entity sends a network data analysis request to the NWDAF entity. The network data analysis request is used to request the NWDAF entity to analyze the network data of the terminal device to obtain the network usage of the terminal device or the status of the terminal.

[0089] S508 acquires network data and obtains network data analysis results;

[0090] In this step, the NWDAF entity acquires network data from the terminal device and analyzes the network data to obtain network data analysis results.

[0091] S510 returns the network data analysis results;

[0092] In this step, the NWDAF entity returns the network data analysis results to the SMF entity.

[0093] S512, PDU session activation or release.

[0094] In this step, the SMF entity determines whether to activate or release the PDU session executing AI tasks and / or ML tasks based on the network data analysis results, and then selects to activate or release the relevant PDU session according to the operation parameters.

[0095] Another PDU session management method disclosed in this embodiment places the decision-making power on whether to execute AI tasks or ML tasks on the network side. Through network intelligence, it realizes dynamic management of PDU sessions executing AI tasks or ML tasks, assists the smooth execution of AI tasks or ML tasks without exposing network data, and at the same time avoids excessive occupation of network resources by AI tasks or ML tasks.

[0096] Based on the same inventive concept, this disclosure also provides a PDU session management device, as shown in the following embodiment. Since the principle by which this device embodiment solves the problem is similar to that of the above-described method embodiment, the implementation of this device embodiment can refer to the implementation of the above-described method embodiment, and repeated details will not be described again.

[0097] Figure 6 This diagram illustrates a PDU session management device according to an embodiment of the present disclosure, such as... Figure 6 As shown, the device, applied to the SMF entity side of the session management function, includes:

[0098] The contract data receiving module 610 is used to receive the contract data of the terminal device sent by the Unified Data Management Function (UDM) entity. The contract data includes operation parameters, which are used to obtain task information of artificial intelligence (AI) tasks and / or machine learning (ML) tasks executed on the terminal device.

[0099] Analysis result acquisition module 620 is used to acquire network data analysis results of terminal devices from the Network Data Analysis Function (NWDAF) entity; and

[0100] The PDU session management module 630 is used to activate or release PDU sessions for terminal devices to perform AI and / or ML tasks based on operating parameters and network data analysis results.

[0101] In one embodiment of this disclosure, the analysis result acquisition module 620 is further configured to send a network data analysis request to the NWDAF entity, wherein the network data analysis request is used to request the NWDAF entity to analyze the network resource utilization and / or terminal status of the terminal device; and to receive the network data analysis results of the terminal device returned by the NWDAF entity.

[0102] In one embodiment of this disclosure, the analysis result acquisition module 620 is further configured to receive network data analysis results returned by the NWDAF entity within a preset time period.

[0103] In one embodiment of this disclosure, the preset duration is the effective duration of the AI ​​task and / or the effective duration of the ML task. The analysis result acquisition module 620 is also used to receive network data analysis results sent by the NWDAF entity within the effective duration of the AI ​​task and / or the effective duration of the ML task.

[0104] In one embodiment of this disclosure, the data analysis results include the network resource utilization and / or terminal status of the terminal device. The PDU session management module 630 is also used to activate or release the PDU session of the terminal device performing AI tasks and / or ML tasks based on the operation parameters, network resource utilization and terminal status.

[0105] Based on the same inventive concept, this disclosure also provides a PDU session management system, as shown in the following embodiments. Since the principle by which this system embodiment solves the problem is similar to that of the above method embodiments, the implementation of this system embodiment can refer to the implementation of the above method embodiments, and repeated details will not be described again.

[0106] Figure 7 This diagram illustrates a PDU session management system according to an embodiment of the present disclosure, such as... Figure 7 As shown, the system includes: Session Management Function (SMF) entity 140, Network Data Analysis Function (NWDAF) entity 110, Unified Data Management (UDM) entity 150, and terminal device 180;

[0107] UDM entity 150 is used to send the subscription data of terminal device 180 to SMF entity 140. The application function AF entity writes the operation parameters of AI tasks and / or ML tasks executed on the terminal device into the subscription data stored on UDM entity 150 through the network open function NEF entity. The subscription data contains operation parameters, which are used to obtain task information of artificial intelligence AI tasks and / or machine learning ML tasks executed on the terminal device.

[0108] NWDAF entity 110 is used to receive network data analysis requests sent by SMF entity 140 and return network data analysis results to SMF entity 140. The network data analysis request is used to request NWDAF entity 110 to analyze the network resource utilization and / or terminal status of the terminal device.

[0109] SMF entity 140 is used to receive contract data and network data analysis results, and to activate or release PDU sessions for terminal devices to perform AI and / or ML tasks based on operating parameters and network data analysis results.

[0110] Those skilled in the art will understand that various aspects of this disclosure can be implemented as a system, method, or program product. Therefore, various aspects of this disclosure can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, collectively referred to herein as a "circuit," "module," or "system."

[0111] The following reference Figure 8 To describe an electronic device 800 according to such an embodiment of the present disclosure. Figure 8 The electronic device 800 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0112] like Figure 8 As shown, the electronic device 800 is manifested in the form of a general-purpose computing device. The components of the electronic device 800 may include, but are not limited to: at least one processing unit 810, at least one storage unit 820, and a bus 830 connecting different system components (including storage unit 820 and processing unit 810).

[0113] The storage unit stores program code, which can be executed by the processing unit 810, causing the processing unit 810 to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure. For example, the processing unit 810 can perform the following steps of the above method embodiments: receiving subscription data of the terminal device sent by the Unified Data Management Function (UDM) entity, wherein the subscription data includes operation parameters, which are used to obtain task information of artificial intelligence (AI) tasks and / or machine learning (ML) tasks executed on the terminal device; obtaining network data analysis results of the terminal device from the Network Data Analysis Function (NWDAF) entity; and activating or releasing the PDU session for the terminal device to execute AI tasks and / or ML tasks based on the operation parameters and the network data analysis results.

[0114] Storage unit 820 may include a readable medium in the form of a volatile storage unit, such as random access memory (RAM) 8201 and / or cache memory 8202, and may further include a read-only memory (ROM) 8203.

[0115] The storage unit 820 may also include a program / utility 8204 having a set (at least one) of program modules 8205, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0116] Bus 830 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0117] Electronic device 800 can also communicate with one or more external devices 840 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 800, and / or with any device that enables electronic device 800 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 850. Furthermore, electronic device 800 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 860. As shown, network adapter 860 communicates with other modules of electronic device 800 via bus 830. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0118] 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 disclosure 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, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0119] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, which may be a readable signal medium or a readable storage medium. A program product capable of implementing the methods described above is stored thereon. In some possible implementations, various aspects of this disclosure may also be implemented as a program product including program code, which, when executed on a terminal device, causes the terminal device to perform the steps according to various exemplary embodiments of this disclosure described in the "Exemplary Methods" section of this specification.

[0120] More specific examples of computer-readable storage media in this disclosure may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0121] In this disclosure, a computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of transmitting, propagating, or transmitting a program for use by or in connection with an instruction execution system, apparatus, or device.

[0122] Optionally, the program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0123] In practical implementation, program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0124] 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 embodiments of this disclosure, 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.

[0125] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0126] 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 disclosure 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, including several instructions to cause a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0127] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the appended claims.< / apiversion>

Claims

1. A method for managing Protocol Data Unit (PDU) sessions, characterized in that, The SMF entities used for session management functions include: Receive subscription data from the terminal device sent by the Unified Data Management (UDM) entity, wherein the subscription data includes operation parameters, and the operation parameters are used to obtain task information of artificial intelligence (AI) tasks and / or machine learning (ML) tasks executed on the terminal device; Obtain the network data analysis results of the terminal device from the Network Data Analysis Function (NWDAF) entity; Based on the operating parameters and the network data analysis results, the PDU session for executing AI tasks and / or ML tasks on the terminal device is activated or released.

2. The Protocol Data Unit (PDU) session management method according to claim 1, characterized in that, The operation parameters are written by the Application Function (AF) entity to the subscription data of the terminal device stored on the UDM entity through the Network Open Function (NEF) entity.

3. The Protocol Data Unit (PDU) session management method according to claim 1, characterized in that, The method further includes obtaining network data analysis results of the terminal device from the Network Data Analysis Function (NWDAF) entity: Send a network data analysis request to the NWDAF entity, wherein the network data analysis request is used to request the NWDAF entity to analyze the network resource utilization and / or terminal status of the terminal device; Receive the network data analysis results of the terminal device returned by the NWDAF entity.

4. The Protocol Data Unit (PDU) session management method according to claim 1, characterized in that, Receive data analysis results sent by the Network Data Analysis Function (NWDAF) entity, including: Receive network data analysis results returned by the NWDAF entity within a preset time period.

5. The Protocol Data Unit (PDU) session management method according to claim 4, characterized in that, The preset duration is the effective duration of the AI ​​task and / or the effective duration of the ML task. It receives network data analysis results returned by the NWDAF entity within the preset duration, including: Receive network data analysis results sent by NWDAF entities within the effective duration of AI tasks and / or ML tasks.

6. The Protocol Data Unit (PDU) session management method according to claim 1, characterized in that, The data analysis results include the network resource utilization and / or terminal status of the terminal device; based on the operating parameters and the network data analysis results, the PDU sessions for executing AI tasks and / or ML tasks on the terminal device are activated or released, including: Based on the operating parameters, network resource utilization, and terminal status, the PDU session for executing AI and / or ML tasks on the terminal device is activated or released.

7. A Protocol Data Unit (PDU) session management device, characterized in that, The device, applied to the SMF entity side of the session management function, includes: The contract data receiving module is used to receive contract data from the terminal device sent by the Unified Data Management (UDM) entity. The contract data includes operation parameters, which are used to obtain task information of artificial intelligence (AI) tasks and / or machine learning (ML) tasks executed on the terminal device. The analysis result acquisition module is used to acquire the network data analysis results of the terminal device from the Network Data Analysis Function (NWDAF) entity; and The PDU session management module is used to activate or release PDU sessions for the terminal device to perform AI tasks and / or ML tasks based on the operation parameters and the network data analysis results.

8. A Protocol Data Unit (PDU) session management system, characterized in that, include: Session management function (SMF) entity, network data analysis function (NWDAF) entity, unified data management (UDM) entity, and terminal devices; The UDM entity is used to send the subscription data of the terminal device to the SMF entity. The Application Function (AF) entity writes the operation parameters of the AI ​​and / or ML tasks executed on the terminal device into the subscription data stored on the UDM entity through the Network Open Function (NEF) entity. The subscription data includes operation parameters, which are used to obtain the task information of the artificial intelligence (AI) tasks and / or machine learning (ML) tasks executed on the terminal device. The NWDAF entity is used to receive network data analysis requests sent by the SMF entity and return network data analysis results to the SMF entity. The network data analysis request is used to request the NWDAF entity to analyze the network resource utilization and / or terminal status of the terminal device. The SMF entity is used to receive the subscription data and the network data analysis results, and based on the operation parameters and the network data analysis results, to activate or release the PDU session for the terminal device to perform AI tasks and / or ML tasks.

9. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the Protocol Data Unit (PDU) session management method of any one of claims 1 to 6 by executing the executable instructions.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the Protocol Data Unit (PDU) session management method according to any one of claims 1 to 6.

Images