Method and apparatus for policy determination

Abstract

A method for strategy determination, comprising: obtaining first data and a label corresponding to the first data based on a digital twin; training an artificial intelligence (AI) model based on the first data and the label corresponding to the first data, the AI model being used to obtain air interface access strategies and / or user plane path selection strategies of a plurality of terminal devices in a network or a region. The method helps to solve the air interface access strategy and user plane path selection problem of the plurality of terminal devices in the network or the region, and further ensures that the overall average service experience of the terminal devices reaches a certain threshold while the network energy consumption is minimized.

Description

Technical Field

[0001] This application relates to the field of communications, and more specifically, to a method and apparatus for determining a strategy. Background Technology

[0002] When terminal devices access the network, network data analytics function (NWDAF) network elements can assist the network in configuring appropriate access policies for them. NWDAF network elements train and generate artificial intelligence (AI) models based on large amounts of acquired data, and then generate data analysis results based on these models. These analysis results can be used to assist the network in policy formulation and execution. For example, NWDAF network elements generate service experience analysis results based on network data and application function (AF) network data. These service experience analysis results help policy control function (PCF) network elements formulate policies related to terminal device services, as well as policy and charging control (PCC) and quality of service (QoS) policies.

[0003] However, existing assisted access technologies typically only formulate access policies based on the service experience of a single terminal device. Once the access policy for one terminal device is determined, conflicts may arise when determining access policies for other terminal devices. Furthermore, considering only service experience inevitably leads to increased network energy consumption, thereby increasing operating costs.

[0004] Therefore, there is an urgent need to provide a technology that can simultaneously formulate access policies for multiple terminal devices within a network, thereby improving the overall service experience of the network and reducing network energy consumption. Summary of the Invention

[0005] This application provides a method and apparatus for policy determination, capable of determining the air interface access policy and / or user plane path selection policy of multiple terminal devices within a region of interest, thereby improving the overall network service experience and reducing network energy consumption.

[0006] In a first aspect, a method for determining a strategy is provided, comprising: obtaining first data and the corresponding label based on a digital twin; and training an artificial intelligence (AI) model based on the first data and the corresponding label, wherein the AI ​​model is used to obtain the air interface access strategy and / or user plane path selection strategy of multiple terminal devices within a network or region.

[0007] The technical solution of this application, which uses a method to train and generate AI models based on digital twin networks, helps to solve the problems of air interface access strategies and user plane path selection for multiple terminal devices within a network or region. Furthermore, it can also ensure that the overall average service experience of these terminal devices reaches a certain threshold while minimizing network energy consumption.

[0008] Optionally, the model can also be used to obtain the service quality parameter allocation strategy for multiple terminal devices within a network or region.

[0009] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: obtaining second data from a data provider, wherein the data provider includes an Operation, Management and Maintenance (OAM) system, a Network Functions (NF) network element, and a Radio Access Network (RAN) network element; and generating a digital twin based on the second data.

[0010] In this way, the low-cost trial-and-error and intelligent decision-making characteristics of digital twins can be utilized to obtain a large amount of training datasets in the digital twins to train and generate AI models, thereby obtaining better output information, such as air interface access strategies and / or user plane path selection strategies for multiple terminal devices within a network or region.

[0011] Optionally, obtaining the first data and the corresponding tag based on the digital twin specifically includes: obtaining the first data based on the digital twin; and obtaining the tag corresponding to the first data based on the first data and the digital twin.

[0012] The first data includes at least one of the following historical information of multiple terminal devices within the network or the area: location information, service information, reference signal received power (RSRP) information, reference signal received quality (RSRQ) information, and signal interference noise ratio (SINR) information.

[0013] The second data includes at least one of the following: topology information between network devices within a network or area, connection information between terminal devices and network devices within a network or area, device information or status information of network devices, and device information or status information of terminal devices.

[0014] Network equipment includes at least one of the following: RAN network element, Access and Mobility Management Function (AMF) network element, Session Management Function (SMF) network element, and User Plane Function (UPF) network element.

[0015] When a network device includes a RAN element, the device information or status information of the network device may include: the identity information and service area information of the RAN element; the device information or status information of the terminal device may include: RSRP, RSRQ and SINR information of multiple terminal devices in the area.

[0016] When a network device includes an AMF network element, the device information or status information of the network device may include: the identity information and service area information of the AMF network element. The device information or status information of the terminal device may include: the location information of multiple terminal devices within the area.

[0017] When a network device includes an SMF network element, the device information or status information of the network device may include: the identity information and service area information of the SMF network element. The device information or status information of the terminal device may include: the service information of multiple terminal devices in the area.

[0018] When a network device includes a UPF network element, the device information or status information of the network device may include: the identity information of the UPF network element, service area information, quality of service (QoS) flow bandwidth information, packet loss rate, and latency information.

[0019] In a second aspect, a method for determining a strategy is provided, comprising: acquiring third data, the third data including at least one of the following current information of multiple terminal devices within a network or region: location information, service information, reference signal received power (RSRP) information, reference signal received quality (RSRQ) information, and signal interference noise ratio (SINR) information; inputting the third data into an artificial intelligence (AI) model to acquire air interface access strategies and / or user plane path selection strategies of multiple terminal devices within the network or region, wherein the AI ​​model can be trained by the method described in any one of the first aspects.

[0020] The technical solution of this application, which uses a method to train and generate AI models based on digital twin networks, helps to solve the problems of air interface access strategies and user plane path selection for multiple terminal devices within a network or region. Furthermore, it can also ensure that the overall average service experience of these terminal devices reaches a certain threshold while minimizing network energy consumption.

[0021] In conjunction with the second aspect, in some implementations of the second aspect, the method further includes: obtaining the service quality parameter allocation strategy for multiple terminal devices within the network or region.

[0022] Optionally, when the method is executed by the Network Data Analysis (NWDAF) network element, obtaining third data specifically includes: obtaining third data from a data provider, wherein the data provider includes the Operation, Management and Maintenance (OAM) system, the Network Functions (NF) network element, and the Radio Access Network (RAN) network element; or, obtaining third data based on prediction of first data, wherein the first data includes at least one of the following historical information of multiple terminal devices within the network or the area: location information, service information, Reference Signal Received Power (RSRP) information, Reference Signal Received Quality (RSRQ) information, and Signal-to-Interference-Noise Ratio (SINR) information.

[0023] When the method is executed by an NWDAF network element, the method further includes: receiving first information, the first information being used to request air interface access policies and / or user plane path selection policies for multiple terminal devices within the network or the area; sending second information, the second information including air interface access policies and / or user plane path selection policies for multiple terminal devices within the network or the area; or, sending the neural network model.

[0024] The first information can also be used to request service quality configuration policies for multiple terminal devices within the network or region.

[0025] Optionally, the first information can also be used to request filtering information, service experience information, and / or network energy consumption information, wherein the filtering information is used to indicate the scope of application of the policy.

[0026] Accordingly, in response to the first information, the second information may also include the service quality configuration policies for multiple terminal devices within the network or area.

[0027] Optionally, the second information may also include at least one of the following: validity period information, service experience information, and network energy consumption information.

[0028] Thirdly, a method for determining a strategy is provided, including: sending first information, the first information being used to request air interface access strategies and / or user plane path selection strategies for multiple terminal devices within a network or area;

[0029] Receive second information, which includes air interface access policies and / or user plane path selection policies for multiple terminal devices within the network or area; or,

[0030] Receive AI model, which is used to obtain the air interface access policy and / or user plane path selection policy of multiple terminal devices within the network or area.

[0031] The first information is also used to request service quality configuration policies for multiple terminal devices within the network or the area.

[0032] Optionally, the first information can also be used to request filtering information, service experience information, and / or network energy consumption information, wherein the filtering information is used to indicate the scope to which the policy applies.

[0033] Accordingly, in response to the first information, the second information may also include the service quality configuration policies for multiple terminal devices within the network or area.

[0034] Optionally, the second information may also include at least one of the following: validity period information, service experience information, and network energy consumption information.

[0035] Fourthly, a policy determination apparatus is provided, comprising: a processing unit, configured to acquire first data and a tag corresponding to the first data based on a digital twin; the processing unit is further configured to train an artificial intelligence (AI) model based on the first data and the tag corresponding to the first data, the AI ​​model being used to acquire air interface access policies and / or user plane path selection policies of multiple terminal devices within a network or region.

[0036] The technical solution of this application, which uses a method to train and generate AI models based on digital twin networks, helps to solve the problems of air interface access strategies and user plane path selection for multiple terminal devices within a network or region. Furthermore, it can also ensure that the overall average service experience of these terminal devices reaches a certain threshold while minimizing network energy consumption.

[0037] Optionally, the AI ​​model can also be used to obtain the service quality parameter allocation strategy for multiple terminal devices within a network or region.

[0038] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the apparatus further includes: a transceiver unit for acquiring second data from a data provider, wherein the data provider includes an Operation, Management and Maintenance (OAM) system, a Network Functions (NF) network element, and a Radio Access Network (RAN) network element; and a processing unit for generating a digital twin based on the second data.

[0039] In this way, the low-cost trial-and-error and intelligent decision-making characteristics of digital twins can be utilized to obtain a large amount of training datasets in the digital twins to train and generate AI models, thereby obtaining better output information, such as air interface access strategies and / or user plane path selection strategies for multiple terminal devices within a network or region.

[0040] Optionally, the processing unit is specifically used to: obtain first data based on the digital twin; and obtain the tag corresponding to the first data based on the first data and the digital twin.

[0041] The first data includes at least one of the following historical information of multiple terminal devices within the network or the area: location information, service information, reference signal received power (RSRP) information, reference signal received quality (RSRQ) information, and signal interference noise ratio (SINR) information.

[0042] The second data includes at least one of the following: topology information between network devices within a network or area, connection information between terminal devices and network devices within a network or area, device information or status information of network devices, and device information or status information of terminal devices.

[0043] Network equipment includes at least one of the following: RAN network element, Access and Mobility Management Function (AMF) network element, Session Management Function (SMF) network element, and User Plane Function (UPF) network element.

[0044] When a network device includes a RAN element, the device information or status information of the network device may include: the identity information and service area information of the RAN element; the device information or status information of the terminal device may include: the RSRP, RSRQ and SINR information of the terminal device in the area.

[0045] When a network device includes an AMF network element, the device information or status information of the network device may include: the identity information and service area information of the AMF network element; the device information or status information of the terminal device may include: the location information of the terminal device within the area.

[0046] When a network device includes an SMF network element, the device information or status information of the network device may include: the identity information and service area information of the SMF network element; the device information or status information of the terminal device may include: the service information of the terminal device within the area.

[0047] When a network device includes a UPF network element, the device information or status information of the network device may include: the identity information of the UPF network element, service area information, quality of service (QoS) flow bandwidth information, packet loss rate, and latency information.

[0048] Fifthly, a policy determination apparatus is provided, comprising: a transceiver unit for acquiring third data, the third data including at least one of the following current information of multiple terminal devices within a network or area: location information, service information, reference signal received power (RSRP) information, reference signal received quality (RSRQ) information, and signal interference noise ratio (SINR) information; and a processing unit for inputting the third data into an artificial intelligence (AI) model to acquire air interface access policies and / or user plane path selection policies of multiple terminal devices within the network or area, wherein the AI ​​model can be trained by any one of the methods in the first aspect.

[0049] The technical solution of this application, which uses a method to train and generate AI models based on digital twin networks, helps to solve the problems of air interface access strategies and user plane path selection for multiple terminal devices within a network or region. Furthermore, it can also ensure that the overall average service experience of these terminal devices reaches a certain threshold while minimizing network energy consumption.

[0050] In conjunction with the fifth aspect, in some implementations of the fifth aspect, the processing unit is also used to: obtain the service quality parameter allocation strategy for multiple terminal devices within the network or area.

[0051] Optionally, when the device is an NWDAF network element, the transceiver unit is specifically used to: obtain third data from a data provider, wherein the data provider includes an Operation, Management and Maintenance (OAM) system, a Network Functions (NF) network element, and a Radio Access Network (RAN) network element; or, the processing unit is specifically used to: predict and obtain third data based on first data, wherein the first data includes at least one of the following historical information of multiple terminal devices within the network or the area: location information, service information, Reference Signal Received Power (RSRP) information, Reference Signal Received Quality (RSRQ) information, and Signal-to-Interference-Noise Ratio (SINR) information.

[0052] When the device is an NWDAF network element, the transceiver unit is specifically used to: receive first information, which requests air interface access policies and / or user plane path selection policies for multiple terminal devices within the network or the area; send second information, which includes air interface access policies and / or user plane path selection policies for multiple terminal devices within the network or the area; or, send the neural network model.

[0053] The first information can also be used to request service quality configuration policies for multiple terminal devices within the network or region.

[0054] Optionally, the first information can also be used to request filtering information, service experience information, and / or network energy consumption information, wherein the filtering information is used to indicate the scope of application of the policy.

[0055] Accordingly, in response to the first information, the second information may also include the service quality configuration policies for multiple terminal devices within the network or area.

[0056] Optionally, the second information may also include at least one of the following: validity period information, service experience information, and network energy consumption information.

[0057] A sixth aspect provides a policy determination apparatus, comprising: a transceiver unit configured to transmit first information, the first information being used to request air interface access policies and / or user plane path selection policies of multiple terminal devices within a network or area; the transceiver unit is further configured to receive second information, the second information including air interface access policies and / or user plane path selection policies of multiple terminal devices within a network or area; or, the transceiver unit is further configured to receive an AI model, the AI ​​model being used to obtain air interface access policies and / or user plane path selection policies of multiple terminal devices within a network or area.

[0058] The first information is also used to request service quality configuration policies for multiple terminal devices within the network or the area.

[0059] Optionally, the first information can also be used to request filtering information, service experience information, and / or network energy consumption information, wherein the filtering information is used to indicate the scope to which the policy applies.

[0060] Accordingly, in response to the first information, the second information may also include the service quality configuration policies for multiple terminal devices within the network or area.

[0061] Optionally, the second information may also include at least one of the following: validity period information, service experience information, and network energy consumption information.

[0062] A seventh aspect provides a strategy-determining apparatus, comprising: a processor coupled to a memory for storing programs or instructions, which, when executed by the processor, cause the apparatus to implement a method as described in any of the first to third aspects and various implementations thereof.

[0063] Optionally, there may be one or more processors and one or more memories.

[0064] Optionally, the memory can be integrated with the processor, or the memory can be separated from the processor.

[0065] Eighthly, a communication system is provided, including a data analysis network element, a method for performing any one of the first to third aspects and various implementations thereof, and a core network element for communicating with the data analysis network element.

[0066] A ninth aspect provides a computer-readable medium storing a computer program (also referred to as code or instructions) that, when run on a computer, causes the computer to perform the methods of any of the first to third aspects and their possible implementations described above.

[0067] In a tenth aspect, a computer program product is provided, the computer program product comprising: a computer program (also referred to as code or instructions), which, when the computer program is run, causes a computer to perform the methods of any of the first to third aspects and their possible implementations described above.

[0068] It should be noted that the above-mentioned computer program code can be stored in whole or in part on the first storage medium, wherein the first storage medium can be packaged together with the processor or packaged separately from the processor. This application embodiment does not specifically limit this.

[0069] Eleventhly, a chip system is provided, including a memory and a processor, the memory for storing a computer program and the processor for calling and running the computer program from the memory, such that a communication device equipped with the chip system performs the methods of any of the first to third aspects and their possible implementations described above.

[0070] The chip system may include input circuits or interfaces for transmitting information or data, and output circuits or interfaces for receiving information or data. Attached Figure Description

[0071] Figure 1 This is a schematic diagram of a communication system applicable to embodiments of this application.

[0072] Figure 2 This is a schematic structural diagram of an example of the algorithm flow provided in this application.

[0073] Figure 3 This is an example of a schematic flowchart of the model training process provided in this application.

[0074] Figure 4 This is another illustrative interactive diagram of the strategy determination process provided in this application.

[0075] Figure 5 This is another illustrative interactive diagram illustrating the strategy determination process provided in this application.

[0076] Figure 6 This is a schematic block diagram of an example of the strategy determination device provided in this application.

[0077] Figure 7 This is another schematic block diagram of the strategy determination device provided in this application.

[0078] Figure 8 This is a schematic structural diagram of an example of the strategy determination device provided in this application. Detailed Implementation

[0079] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0080] The technical solutions of this application can be applied to various communication systems, such as: Long Term Evolution (LTE) system, LTE Frequency Division Duplex (FDD) system, LTE Time Division Duplex (TDD) system, Universal Mobile Telecommunication System (UMTS), 5th Generation (5G) system, future 5.5th Generation (5.5G), 6th Generation (6G) system, or New Radio (NR) system, etc.

[0081] The following uses the fifth-generation system as an example, combined with... Figure 1 This application describes a suitable network architecture based on a network data analytics function (NWDAF).

[0082] like Figure 1 As shown, the communication system includes, but is not limited to, the following network elements:

[0083] 1. Terminal equipment

[0084] The terminal equipment in this application embodiment can also be referred to as: user equipment (UE), mobile station (MS), mobile terminal (MT), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication equipment, user agent, or user device, etc.

[0085] Terminal devices can be devices that provide voice / data connectivity to users, such as handheld devices with wireless connectivity, in-vehicle devices, etc. Currently, examples of terminals include: mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving or autopilot systems, 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 wireless modems, in-vehicle devices, wearable devices, terminal devices in future 5G networks, or future evolved public land mobile communication networks. Terminal devices in a mobile network (PLMN), etc., are not limited to this in the embodiments of this application.

[0086] By way of example and not limitation, in this embodiment, the terminal device can also be a wearable device. Wearable devices, also known as wearable smart devices, are a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are feature-rich, large in size, and can achieve complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those that focus on a specific type of application function and require the use of other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring. Furthermore, in this embodiment, the terminal device can also be a terminal device in an Internet of Things (IoT) system.

[0087] 2. Radio Access Network (RAN)

[0088] A radio access network (RAN) is an access network that implements network access functions based on wireless communication technology. RAN manages radio resources, provides wireless or air interface access services to terminals, and facilitates the forwarding of control signals and user data between terminals and the core network.

[0089] As an example and not a limitation, the radio access network can be an evolved NodeB (eNB or eNodeB) in an LTE system, a radio controller in a cloud radio access network (CRAN) scenario, or the access device can be a relay station, access point, vehicle-mounted equipment, wearable device, or access device in a 5G network or an access device in a future evolved PLMN network, etc. It can be an access point (AP) in a WLAN, or a gNB in ​​an NR system. This application embodiment is not limited.

[0090] In addition, in the embodiments of this application, when the UE accesses the RAN, it is necessary to select an appropriate air interface access strategy for the UE, such as the selection of radio access technology (RAT) and frequency.

[0091] 3. Session Management Function (SMF) network element

[0092] The session management function network element is mainly used for session management, allocation and management of Internet Protocol (IP) addresses for terminal devices, selection of manageable user plane function (UPF) network elements, endpoints for policy control and charging function interfaces, and downlink data notification. In the embodiments of this application, it can be used to implement the functions of the session management network element.

[0093] 4. Access and Mobility Management Function (AMF) network element

[0094] Access and mobility management function network elements are mainly used for mobility management and access management, and can be used to implement other functions of the mobility management entity (MME) besides session management, such as lawful interception or access authorization (or authentication). In the embodiments of this application, they can be used to implement the functions of access and mobility management network elements.

[0095] It should be understood that in the embodiments of this application, the aforementioned AMF and SMF, as well as some other data providers, can also be referred to as data provider network elements. These data provider network elements typically refer to nodes and physical devices in the network, which provide corresponding functional support for UE access to the network, conduct sessions, authentication, policy control, etc., and also generate corresponding network data.

[0096] 5. User plane function (UPF)

[0097] User plane function network elements can be used for packet routing and forwarding, or QoS parameter processing of user plane data, etc. User data can access the data network (DN) through this network element. In the embodiments of this application, it can be used to implement the functions of user plane network elements. For example, when establishing a session on different UPFs, the UE's service experience will be different. Therefore, the aforementioned SMF needs to select a suitable UPF for the UE's session.

[0098] 6. Data Network (DN)

[0099] A data network refers to a specific data service network that a UE accesses. For example, typical data networks include the Internet and the IP Multimedia Subsystem (IPMS).

[0100] 7. Network Data Analytics Function (NWDAF)

[0101] The Network Data Analysis Function (NWDAF) network element possesses at least one of the following functions: data collection, model training, analysis result inference, and analysis result feedback. The data collection function refers to collecting data from network elements, third-party service servers, terminal devices, or network management systems. The model training function involves training a model based on relevant input data. The analysis result inference function uses the trained model and inference data to determine the data analysis results. Finally, the analysis result feedback function provides the data analysis results to network elements, third-party service servers, terminal devices, or network management systems. These results can assist the network in selecting service quality parameters, performing traffic routing, or selecting background traffic transmission strategies. This application primarily focuses on the data collection and model training functions of the NWDAF.

[0102] In the embodiments of this application, the NWDAF can be a separate network element or it can be co-located with other core network elements. For example, the NWDAF network element can be co-located with the access and mobility management function (AMF) network element or with the session management function (SMF) network element.

[0103] Typical application scenarios for NWDAF include: Customization or optimization of terminal parameters. NWDAF collects information on user connection management, mobility management, session management, and accessed services, and uses reliable analysis and prediction models to evaluate and analyze different types of users, build user profiles, determine user movement trajectories and service usage habits, and predict user behavior. Based on this analysis and prediction data, the 5G network optimizes user mobility management parameters and radio resource management parameters. Service (path) optimization. NWDAF collects information on network performance, service load in specific areas, and user service experience, and uses reliable network performance analysis and prediction models to evaluate and analyze different types of services, build service profiles, determine the inherent correlation between service quality of experience (QoE), service experience, service path, or 5G quality of service (QoS) parameters, and optimize service paths, service routing, 5G edge computing, and service-to-5G environments. QoS, etc.; AF optimizes service parameters. For example, vehicle-to-everything (V2X) is a crucial technology in 5G networks. In autonomous driving scenarios within V2X, predicting the network performance (e.g., QoS information, traffic load) of base stations the vehicle is about to pass plays a vital role in improving the quality of service in V2X. For instance, V2X servers can determine whether to continue autonomous driving mode based on predicted network performance information. NWDAF collects information such as network performance and traffic load in specific areas, and utilizes reliable network performance analysis and prediction models to statistically analyze and predict network performance, thus assisting AF in optimizing parameters.

[0104] 8. Application Function (AF) Network Element

[0105] Application function network elements are used to provide services, or to perform data routing for application impact, access network open function network elements, or interact with NWDAF network elements to perform policy control, etc.

[0106] 9. Network Repository Function (NRF)

[0107] Network storage function (NF) elements can be used to support network element services or network element discovery functions. They receive NF discovery requests from network function (NF) instances and provide information about the discovered NF instances to the NF instances. They also include NF configuration files used to support the maintenance of available NF instances and their supported services.

[0108] 10. Network Exposure Function (NEF): Used to expose service and network capability information (such as terminal location, session reachability) provided by 3GPP network functions to the outside world.

[0109] 11. Policy control function (PCF)

[0110] Policy control network elements provide a unified policy framework to guide network behavior and offer policy rule information to control plane functional network elements (such as AMF and SMF network elements).

[0111] It should be understood that, in the embodiments of this application, the aforementioned AF, PCF, and other network function (NF) elements that require data analysis results can also be referred to as data analysis result consumers. They can subscribe to the corresponding data analysis results from the NWDAF and make corresponding adjustments based on the data analysis results. For example, the PCF adjusts the QoS parameters of the service based on the service and service experience feedback from the NWDAF, thereby better ensuring the service experience. As another example, the operation, administration, and maintenance (OAM) element evaluates the slice service level agreement (SLA) and adjusts the slice resource configuration (such as air interface, core network, transport network, etc.) based on the service experience of the sliced ​​UEs fed back by the NWDAF.

[0112] In the above network architecture, the N2 interface is the interface between the RAN and AMF network elements, used for transmitting radio parameters and non-access stratum (NAS) signaling; the N3 interface is the interface between the RAN and UPF network elements, used for transmitting user plane data; the N4 interface is the interface between the SMF and UPF network elements, used for transmitting information such as service policies, tunnel identification information for N3 connections, data buffer indication information, and downlink data notification messages. The N6 interface is the interface between the DN and UPF network elements, used for transmitting user plane data. Naf is the service interface provided by AF, Nnrf is the service interface provided by NRF, Nnwdaf is the service interface provided by NWDAF, and Nnef is the service interface provided by NEF.

[0113] It should be understood that the network architecture described above in the embodiments of this application is merely an example of a network architecture described from the perspective of a traditional point-to-point architecture and a service-oriented architecture. The network architecture applicable to the embodiments of this application is not limited to this, and any network architecture that can realize the functions of the above-mentioned network elements is applicable to the embodiments of this application.

[0114] It should be understood that Figure 1 The interface names between the various network elements are merely examples; in actual implementations, the interface names may differ, and this application does not impose any specific limitations on them. Furthermore, the names of the messages (or signaling) transmitted between the aforementioned network elements are also merely examples and do not constitute any limitation on the function of the messages themselves.

[0115] It should be noted that the aforementioned network element may also be referred to as an entity, device, apparatus, or module, etc., and this application does not specifically limit it. Furthermore, in this application, for ease of understanding and explanation, the description of network element is omitted in some descriptions. For example, the NWDAF network element is abbreviated as NWDAF. In this case, "NWDAF" should be understood as the NWDAF network element. The following descriptions of the same or similar cases are omitted.

[0116] It is understood that the aforementioned functional network elements can be network components in hardware devices, software functions running on dedicated hardware, or virtualization functions instantiated on a platform (e.g., a cloud platform).

[0117] It should also be understood that, Figure 1 In the communication system shown, the functions of each component network element are merely exemplary. Not all functions of each component network element are required when applied to the embodiments of this application.

[0118] To assist in network policy formulation and execution, NWDAF acquires relevant data from various domains, including UE, network (e.g., RAN, CN, TN), AF, and OAM. Based on this large amount of acquired data, it trains and generates AI models, and then uses these AI models to generate data analysis results. For example, NWDAF generates service experience analysis results based on AF data. These results help PCF formulate terminal device service-related policies, charging control (PCC), and quality of service (QoS) policies.

[0119] It should be understood that in this application embodiment, AI refers to the technology of presenting human intelligence through computer programs, while machine learning (ML) focuses on developing computer programs that can access data and use that data to learn on their own. In the following description, artificial intelligence and machine learning will not be distinguished. For example, an ML model can also be called an AI model. Optionally, the aforementioned AI model can also be a neural network model, a linear regression model, or other models.

[0120] The main process of building an AI model includes: problem analysis (determining the data to be collected and the type of AI model to be used), data collection, model training, and model inference. Model training is the process of using data to determine the parameters of the AI ​​model, while model inference is the process of using the trained AI model to predict the output based on new inputs.

[0121] For current mainstream supervised learning AI models, training the model requires a training dataset, including the model input and the corresponding labels. However, the labels for the training data are sometimes difficult to obtain in actual networks, so it is advisable to obtain them in a digital twin.

[0122] A digital twin network is a virtual representation of a physical network. Based on data, models, and interfaces, it analyzes, diagnoses, simulates, and controls the physical network, enabling real-time interactive mapping between the physical and virtual twin networks. It can be used to digitally mirror or simulate the structure, deployment, network status, and business processes of a real network. In some application scenarios, a digital twin network may also be called a digital twin entity; this application does not limit its specific name. The value of a digital twin network:

[0123] (1) Low-cost trial and error. Network structures are becoming increasingly complex, and optimizing them in real-world networks is costly and has a significant impact on the network. In a digital twin, trial and error can be conducted without risk, and network optimization solutions can be found quickly.

[0124] (2) Intelligent decision-making. The digital twin network can assess the current situation, diagnose the past, and predict the future, providing more comprehensive decision support.

[0125] (3) High-efficiency innovation. Helps researchers explore network innovations efficiently, and assists operators in quickly deploying new technologies and reducing risks.

[0126] Therefore, embodiments of this application consider trying various different UE access schemes in a digital twin network. Figure 2 This is a schematic diagram of the algorithm flow of an embodiment of this application. It should be understood that... Figure 2 The algorithm flow shown is merely an example and should not be construed as limiting this application. The AI ​​model related to this application can also be trained using other algorithm flows. Figure 2In the diagram, α1 represents the number of users (e.g., UEs) within the area of ​​interest (AOI), the user location distribution, and the user service distribution; α2 represents the reference signal received power (RSRP), reference signal received quality (RSRQ), and signal-to-interference-and-noise ratio (SINR) information for each UE; β represents the air interface access policy and user plane (UP) path selection scheme for each UE. The output value of the AI ​​model. H(x) represents the optimal UE access scheme corresponding to the current network information α1 and α2 found in the digital twin, which can also be called the optimal solution; H(x) represents the (weighted) average service experience of UEs in the entire network, and Q(π) represents the network energy consumption.

[0127] Training an AI model can yield the optimal UE air interface access strategy and UP path selection scheme based on information (α1 and α2) in the current network. The AI ​​model mentioned above refers to a supervised model (such as a deep neural network). When training an AI model, it is necessary to have model inputs α1 and α2 and their corresponding labels. The model inputs α1 and α2 can be obtained from the actual network, but the optimal access schemes corresponding to α1 and α2 are different. It is difficult to obtain in a real network, so it needs to be obtained in a digital twin network.

[0128] In a digital twin network, the optimal access scheme corresponding to the current network information α1 and α2 is obtained. The approach is as follows: In the digital twin network, fix α1 and α2, continuously adjust the β parameter, and find a scheme that maximizes H(x) while minimizing Q(π), which is the optimal UE access scheme. and These will be used as labels corresponding to training data α1 and α2 to train the AI ​​model.

[0129] In this embodiment of the application, the digital twin is obtained The process is a multi-objective optimization process, and multi-objective optimization processes usually correspond to multiple different solutions. Therefore, it is necessary to determine a standard as the optimal solution based on actual needs. As an example and not a limitation, in this embodiment, we can define the optimal solution as: the solution that minimizes energy consumption among all solutions where the (weighted) average service experience is greater than a certain threshold (e.g., the threshold can be 3.5). Furthermore, if multiple β values ​​are close to the optimal solution, we can choose the solution with the smallest (weighted) variance of user experience, thereby obtaining a more stable and reliable user experience. Of course, we can also adopt other methods to select our optimal solution to meet different requirements for user experience and network energy consumption, and this application does not limit such methods.

[0130] For ease of understanding, Figure 3 A simplified schematic flowchart illustrating the model training process provided in this application is shown below. Figure 3 As shown, in S110, the first data and the tag corresponding to the first data are obtained based on the digital twin.

[0131] The first data includes historical data α1 and α2. α1 represents the number of users (e.g., UEs) in the area of ​​interest, the distribution of user locations, and the distribution of user services. α2 represents the RSRP information, RSRQ information, and SINR information of each UE.

[0132] It should be understood that α1 and α2 are used for ease of description and are a simple classification of the first data. In practical applications, they may not be classified. That is, the first data includes at least one of the following historical information of multiple terminal devices in the network or the area: location information, service information, reference signal received power (RSRP) information, reference signal received quality (RSRQ) information, and signal interference noise ratio (SINR) information.

[0133] It should be understood that NWDAF can also acquire primary data in another way, namely by obtaining a large amount of primary data from data providers, namely the aforementioned historical data α1 and α2. For example, obtaining the UE's location information from the AMF, the UE's service type information from the SMF, and the UE's air interface related information from the RAN, etc. This method requires multiple acquisitions to obtain a large amount of historical data α1 and α2 to meet the purpose of training the AI ​​model.

[0134] After acquiring a large amount of initial data, the labels corresponding to the initial data can be obtained from the digital twin. Specifically, for supervised learning AI models, the training dataset includes two parts: model input and the corresponding labels (i.e., output), which are the initial data and their corresponding labels. NWDAF network elements can obtain the corresponding labels from the digital twin based on the input data α1 and α2 (i.e., the initial data). (i.e., the tag corresponding to the first data, the optimal UE access scheme), repeating this process, can yield a large number of (α1, α2, ... This dataset will be used as training data to train an AI model.

[0135] After obtaining a large amount of initial data and the corresponding labels, NWDAF can execute S120 to train and generate an AI model based on the initial data and the corresponding labels.

[0136] This AI model can be used to obtain the air interface access policies and / or user plane path selection policies of multiple terminal devices within a network or region.

[0137] Optionally, the model can also be used to obtain the service quality parameter allocation strategy for multiple terminal devices within the network or the area.

[0138] The technical solution of this application, which uses a method to train and generate AI models based on digital twin networks, helps to solve the problems of air interface access strategies and user plane path selection for multiple terminal devices within a network or region. Furthermore, it can also ensure that the overall average service experience of these terminal devices reaches a certain threshold while minimizing network energy consumption.

[0139] The above describes the method for training an AI model according to embodiments of this application. The following will combine... Figure 4 and Figure 5 Describe in detail the technical solution determined by the strategy of this application.

[0140] Figure 4 Another schematic interactive diagram illustrating the strategy determination process provided in this application is shown. For example... Figure 4 As shown,

[0141] S210, NWDAF network element acquires second data.

[0142] The second data can be collected from the network by the NWDAF network element, and the source of the second data is not limited in this embodiment. As one possible implementation, the NWDAF acquiring the second data may mainly include the following:

[0143] (1) Topology information between network devices within an area or network collected from OAM: for example, the connection relationships between AMF, SMF, and UPF;

[0144] (2) Data collected from RAN network elements: For example, the identity information and service area information of RAN network elements, and the RSRP, RSRQ and SINR information of terminal devices within the network or area;

[0145] (3) Data collected from AMF network elements: For example, the identity information and service area information of AMF network elements, and the location information of terminal devices within the network or area;

[0146] (4) Data collected from SMF network elements: For example, the identity information and service area information of SMF network elements, and the service information of terminal devices within the network or area;

[0147] (5) Data collected from UPF network elements: For example, the identity information of UPF network elements, service area information, quality of service (QoS) flow bandwidth information, packet loss rate and latency information.

[0148] After obtaining the second data mentioned above, the NWDAF network element can execute step S220 to establish a digital twin based on the collected second data.

[0149] In this application embodiment, a digital twin is a virtual representation of a physical network. It can analyze, judge, simulate and control the physical network based on data, models and interfaces, realize real-time interactive mapping between the physical network and the virtual twin network, and can update parameters according to the real network. It can be used for the structure or function of digital mirror or digital analog network deployment, network status and business processes.

[0150] S230, Receive first information. This first information comes from a subscriber of data analysis results who requested the access scheme from NWDAF, such as SMF or PCF.

[0151] This first piece of information includes analytics ID and filtering information. The analytics ID indicates the type of data analysis result the user is interested in.

[0152] In this embodiment, this step is the process by which a data analysis result subscriber requests the air interface access policy and user plane path selection scheme for terminal devices within the area of ​​interest from the NWDAF network element. Therefore, analytics ID = accesspolicy and / or UP paths. A data analysis result subscriber can request two policies simultaneously, i.e., analytics ID = access policy and UP paths; or a data analysis result subscriber can request one policy, for example, the PCF requests the air interface access policy (analytics ID = access policy), and the SMF requests the UP path selection scheme (analytics ID = UP paths).

[0153] Optionally, subscribers to data analytics results can also request service quality parameter allocation strategies (analytics ID = QoS profile) for multiple terminal devices within the area of ​​interest from the NWDAF network element. This service quality parameter allocation strategy can provide service quality flow configuration information for each terminal device within the area of ​​interest, such as configuration information for QoS parameters like the 5G QoS identifier (5QI), allocation and retention priority (ARP), guaranteed flow bit rate (GFBR), and maximum flow bit rate (MFBR).

[0154] Filtering information can be used to limit the scope of data analysis or to indicate the applicability of data analysis results; this scope can also be called the region of interest. This application does not limit the specific form of the filtering information. For example, the filtering information can be a list of UEs, with data analysis performed only on the UEs in the list, or the data analysis results only applicable to the UEs in the list. Similarly, filtering information can also have other division forms, such as a UE group, or UEs within a network slice.

[0155] Optionally, the aforementioned first information may further include a service experience threshold, scheme validity period information, and network energy consumption information. The service experience threshold can be used to provide a basis for NWDAF network elements to find the optimal access scheme in the digital twin. For example, as described above, obtaining... The process is a multi-objective optimization process, requiring the selection of the solution that minimizes energy consumption from all solutions where the (weighted) average service experience exceeds a threshold. Here, the threshold refers to the service experience threshold information provided by the user to the NWDAF. Furthermore, depending on the different requirements of subscribers based on the data analysis results, the service experience threshold can take different forms. For example, the service experience threshold can be the average service experience threshold of multiple UEs within a region, thus maximizing the service experience for UEs within that region. Similarly, to meet the needs of certain specific UEs, the service experience threshold can also be the service experience threshold for those specific UEs. Additionally, the service experience threshold can also be the weighted average service experience threshold of multiple UEs, and so on, which will not be elaborated upon here.

[0156] To train the AI ​​model, the NWDAF network element can execute S240 to obtain the first data and the label corresponding to the first data.

[0157] The first data includes α1 and α2, where α1 represents the number of users (e.g., UEs) in the area of ​​interest, the distribution of user locations, and the distribution of user services, and α2 represents the RSRP information, RSRQ information, and SINR information of each UE.

[0158] It should be understood that NWDAF can acquire the first data in two ways: one is similar to step S210, acquiring a large amount of historical α1 and α2 data from the data provider. For example, acquiring the UE's location information from the AMF, the UE's service type information from the SMF, and the UE's air interface related information from the RAN. Unlike step S210, which is a single acquisition, this step requires acquiring α1 and α2 multiple times to obtain a large amount of historical data to meet the purpose of training the AI ​​model. The other way utilizes the simulation capability of digital twins, that is, a large amount of α1 and α2 can be generated in the digital twin, which can also be called historical α1 and α2 for easy distinction, to train the AI ​​model.

[0159] After obtaining a large amount of initial data and the corresponding labels, NWDAF can execute S250 to train and generate an AI model.

[0160] Specifically, for supervised learning AI models, the training dataset consists of two parts: the model input and the corresponding labels (i.e., the output), that is, the first data and its corresponding label. NWDAF network elements can obtain the corresponding labels in the digital twin based on the input data α1 and α2. (i.e., the optimal UE access scheme), repeating this process yields a large number of (α1, α2, ...) This dataset will be used as training data to train an AI model.

[0161] The AI ​​model mentioned above can be an ML model, a neural network model, a linear regression model, or other models that can achieve the above functions.

[0162] After training and obtaining the AI ​​model, the NWDAF network element can use the AI ​​model to infer the access scheme for each UE within the area of ​​interest. During model inference, the NWDAF network element can execute step S260 to obtain third data, which is the current data α1 and α2 of the network. The third data can be obtained from the network or predicted from the first data, that is, the current α1 and α2 are predicted based on the historical data of α1 and α2.

[0163] After obtaining the current network data α1 and α2, the NWDAF network element can execute step S270, using the current α1 and α2 as input to the AI ​​model to infer the current access scheme for each UE.

[0164] Optionally, the AI ​​model can also output information related to the access scheme, such as the scheme's validity period, service experience information, and network energy consumption information.

[0165] The validity period of the access plan indicates the effective time interval of the aforementioned access plan. Plans exceeding the validity period will be considered invalid, thus ensuring the feasibility of the plan. Service experience information is obtained in the digital twin after NWDAF infers the real-time or predicted UE access plan using an AI model. This information includes the (weighted) average service experience of UEs within the corresponding AOI and the variance of service experience within the AOI. This information is used to indicate the potential service experience effect of the provided UE access plan, such as the aforementioned service experience threshold. Similarly, network energy consumption information can be used to indicate the potential network energy consumption required by the provided UE access plan.

[0166] S280, send the second message.

[0167] After obtaining the user access scheme, the NWDAF network element can send a second message to the subscribers of the data analysis results to provide feedback. This second message includes a list of air interface access policies for multiple UEs and a list of user plane path selection schemes. It may also include other information, such as scheme validity period, service experience information, and network energy consumption information.

[0168] S290, The data analysis results subscriber establishes a connection for the UE.

[0169] Upon receiving the second information provided by the NWDAF, the data analysis result subscriber can establish corresponding air interface connections and user plane connections for the UE, either independently or through other network elements, based on the air interface access policy and UP path selection scheme fed back by the NWDAF. For example, when the aforementioned data analysis result subscriber is the PCF, the PCF can formulate reasonable RFSP index values ​​for each UE within the AOI according to the air interface access policy, and send these RFSP index values ​​to the RAN via the AMF, so that the RAN can select an appropriate RAT radio access technology / frequency for each UE based on the RFSP index values. As another example, when the aforementioned data analysis result subscriber is the SMF, the SMF can select an appropriate UPF and / or DN for the PDU session of each UE within the AOI according to the user plane path selection scheme.

[0170] The technical solution of this application, which uses a method to train and generate AI models based on digital twin networks, helps to solve the problems of air interface access strategies and user plane path selection for multiple terminal devices within a network or region. Furthermore, it can also ensure that the overall average service experience of these terminal devices reaches a certain threshold while minimizing network energy consumption.

[0171] In the above process, NWDAF is responsible for both the training and inference of the AI ​​model, and sends the inference results to the data analysis result subscribers. In practical applications, however, the training and inference processes of the AI ​​model can also be implemented separately, with NWDAF handling the training and the data analysis result subscribers performing the model's inference. For example... Figure 5 This is another example of an interactive diagram illustrating the strategy determination process provided in this application.

[0172] exist Figure 5 In the middle, steps S310 to S350 and Figure 4 Steps S210 to S250 described herein are the same and will not be repeated here.

[0173] In response to the first information, NWDAF can execute step S360, sending the AI ​​model trained in steps S310 to S350 to the data analysis result subscriber, who can then generate an access scheme for multiple terminal devices within the network / area based on actual needs.

[0174] Optionally, subscribers to the data analytics results can also generate a QoS parameter allocation strategy (analytics ID = QoS profile) for multiple terminal devices within the network / area, based on actual needs. This QoS parameter allocation strategy can provide QoS flow configuration information for each terminal device within the area of ​​interest, such as the configuration information for QoS parameters like 5G QoS identifier 5QI, allocation and reservation priority ARP, guaranteed flow bit rate GFBR, and maximum flow bit rate MFBR.

[0175] In S370, the data analysis results subscriber obtains third data, which is acquired from the network by the data analysis results subscriber. This third data is current data α1 and α2, which may specifically include at least one of the following current information from multiple terminal devices within the network or area: location information, service information, reference signal received power (RSRP) information, reference signal received quality (RSRQ) information, and signal-to-interference-noise ratio (SINR) information.

[0176] After obtaining the current network data α1 and α2, the data analysis result subscriber can perform step S380, using the current α1 and α2 as input to the AI ​​model to infer the current access scheme for each UE.

[0177] Optionally, the AI ​​model can also output information related to the access scheme, such as the scheme's validity period, service experience information, and network energy consumption information.

[0178] The validity period of the access plan indicates the effective time interval of the aforementioned access plan. Plans exceeding the validity period will be considered invalid, thus ensuring the feasibility of the plan. Service experience information is obtained in the digital twin after NWDAF infers the real-time or predicted UE access plan using an AI model. This information includes the (weighted) average service experience of UEs within the corresponding AOI and the variance of service experience within the AOI. This information is used to indicate the potential service experience effect of the provided UE access plan, such as service experience thresholds. Similarly, network energy consumption information can be used to indicate the potential network energy consumption required by the provided UE access plan.

[0179] After obtaining the target access scheme, the data analysis result subscriber can establish corresponding air interface connections and user plane connections for the UE, either independently or through other network elements, based on the air interface access policy and UP path selection scheme derived from AI model inference. For example, when the data analysis result subscriber is a PCF, the PCF can formulate reasonable RFSP index values ​​for each UE within the AOI according to the air interface access policy, and send these RFSP index values ​​to the RAN via the AMF, so that the RAN can select appropriate RAT radio access technology / frequency for each UE based on the RFSP index values. As another example, when the data analysis result subscriber is an SMF, the SMF can select appropriate UPF and / or DN for the PDU session of each UE within the AOI according to the user plane path selection scheme.

[0180] The technical solution of this application, which uses a method to train and generate AI models based on digital twin networks, helps to solve the problems of air interface access strategies and user plane path selection for multiple terminal devices within a network or region. Furthermore, it can also ensure that the overall average service experience of these terminal devices reaches a certain threshold while minimizing network energy consumption.

[0181] It should be understood that the specific examples in the embodiments of this application are only for the purpose of helping those skilled in the art to better understand the embodiments of this application, and are not intended to limit the scope of the embodiments of this application.

[0182] It should also be understood that the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0183] It should also be understood that, in the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced by each other, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0184] It is understood that the method implemented by the communication device in the above embodiments of this application can also be implemented by a component (such as a chip or circuit) that can be configured inside the communication device.

[0185] The above, combined with Figures 3 to 5 This application provides a detailed description of the strategy determination method provided in its embodiments. The method is primarily described from the perspective of interaction between various network elements. It is understood that each network element, in order to achieve the aforementioned functions, includes corresponding hardware structures and / or software modules for executing those functions. Those skilled in the art should recognize that, based on the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed via hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0186] The following, combined with Figures 6 to 8 This application provides a detailed description of the strategy determination apparatus provided in its embodiments. It should be understood that the descriptions of the apparatus embodiments correspond to the descriptions of the method embodiments; therefore, any content not described in detail can be found in the above method embodiments. For brevity, some content is omitted hereafter.

[0187] This application embodiment can divide the transmitting or receiving device into functional modules according to the above method examples. For example, each function can be divided into its own functional modules, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods. The following description uses the division of functional modules according to each function as an example.

[0188] Figure 6 This is a schematic block diagram of a strategy determination device 400 provided in this application.

[0189] The strategy determination device includes a receiving unit 410, a processing unit 420, and a sending unit 430. The strategy determination device 400 can be a data analysis device in the above method embodiment, or it can be a chip used to implement the functions of the data analysis device in the above method embodiment.

[0190] It should be understood that the strategy determination device 400 may correspond to the data analysis device in methods 100 to 300 according to embodiments of this application, and the strategy determination device 400 may include tools for performing... Figures 3 to 5 The data analysis device in the unit executes the method. Furthermore, the strategy determines that each unit in the device 400 and the other operations and / or functions described above respectively implement... Figures 3 to 5 The corresponding processes of methods 100 to 300 in the document.

[0191] In one possible design, the strategy determining device 400 can be implemented Figures 3 to 5 Any of the functions possessed by the data analysis device NWDAF in any of the embodiments shown in any of the figures.

[0192] For example, processing unit 420 is used to obtain first data and the tag corresponding to the first data based on the digital twin; processing unit 420 is also used to train an artificial intelligence (AI) model based on the first data and the tag corresponding to the first data, and the AI ​​model is used to obtain the air interface access strategy and / or user plane path selection strategy of multiple terminal devices in the network or area.

[0193] The technical solution of this application, which uses a method to train and generate AI models based on digital twin networks, helps to solve the problems of air interface access strategies and user plane path selection for multiple terminal devices within a network or region. Furthermore, it can also ensure that the overall average service experience of these terminal devices reaches a certain threshold while minimizing network energy consumption.

[0194] Optionally, the AI ​​model can also be used to obtain the service quality parameter allocation strategy for multiple terminal devices within a network or region.

[0195] The device also includes: a receiving unit 410, which obtains second data from a data provider, wherein the data provider includes an Operation, Management and Maintenance (OAM) system, a Network Functions (NF) network element, and a Radio Access Network (RAN) network element; and a processing unit 420, which is further configured to generate a digital twin based on the second data.

[0196] In this way, the low-cost trial-and-error and intelligent decision-making characteristics of digital twins can be utilized to obtain a large amount of training datasets in the digital twins to train and generate AI models, thereby obtaining better output information, such as air interface access strategies and / or user plane path selection strategies for multiple terminal devices within a network or region.

[0197] Optionally, the processing unit 420 is specifically used to: obtain first data based on the digital twin; and obtain the tag corresponding to the first data based on the first data and the digital twin.

[0198] The first data includes at least one of the following historical information of multiple terminal devices within the network or the area: location information, service information, reference signal received power (RSRP) information, reference signal received quality (RSRQ) information, and signal interference noise ratio (SINR) information.

[0199] The second data includes at least one of the following: topology information between network devices within a network or area, connection information between terminal devices and network devices within a network or area, device information or status information of network devices, and device information or status information of terminal devices.

[0200] Network equipment includes at least one of the following: RAN network element, Access and Mobility Management Function (AMF) network element, Session Management Function (SMF) network element, and User Plane Function (UPF) network element.

[0201] When a network device includes a RAN element, the device information or status information of the network device may include: the identity information and service area information of the RAN element; the device information or status information of the terminal device may include: the RSRP, RSRQ and SINR information of the terminal device in the area.

[0202] When a network device includes an AMF network element, the device information or status information of the network device may include: the identity information and service area information of the AMF network element; the device information or status information of the terminal device may include: the location information of the terminal device within the area.

[0203] When a network device includes an SMF network element, the device information or status information of the network device may include: the identity information and service area information of the SMF network element; the device information or status information of the terminal device may include: the service information of the terminal device within the area.

[0204] When a network device includes a UPF network element, the device information or status information of the network device may include: the identity information of the UPF network element, service area information, quality of service (QoS) flow bandwidth information, packet loss rate, and latency information.

[0205] For example, receiving unit 410 is used to acquire third data, which includes at least one of the following current information of multiple terminal devices within the network or area: location information, service information, reference signal received power (RSRP) information, reference signal received quality (RSRQ) information, and signal interference noise ratio (SINR) information; processing unit 420 is used to input the third data into an artificial intelligence (AI) model to acquire the air interface access strategy and / or user plane path selection strategy of multiple terminal devices within the network or area, and the AI ​​model can be trained by the aforementioned method.

[0206] The technical solution of this application, which uses a method to train and generate AI models based on digital twin networks, helps to solve the problems of air interface access strategies and user plane path selection for multiple terminal devices within a network or region. Furthermore, it can also ensure that the overall average service experience of these terminal devices reaches a certain threshold while minimizing network energy consumption.

[0207] Processing unit 420 is also used to: obtain the service quality parameter allocation strategy for multiple terminal devices within the network or area.

[0208] Optionally, the receiving unit 410 is specifically configured to: obtain third data from a data provider, wherein the data provider includes an Operation, Management and Maintenance (OAM) system, a Network Function (NF) network element, and a Radio Access Network (RAN) network element; or, the processing unit 420 is specifically configured to: predict and obtain third data based on first data, wherein the first data includes at least one of the following historical information of multiple terminal devices within the network or the area: location information, service information, Reference Signal Received Power (RSRP) information, Reference Signal Received Quality (RSRQ) information, and Signal-to-Interference-Noise Ratio (SINR) information.

[0209] The receiving unit 410 is specifically configured to: receive first information, which requests air interface access policies and / or user plane path selection policies for multiple terminal devices within the network or the area. The sending unit 430 is configured to send second information, which includes air interface access policies and / or user plane path selection policies for multiple terminal devices within the network or the area; or, send the neural network model.

[0210] The first information can also be used to request service quality configuration policies for multiple terminal devices within the network or region.

[0211] Optionally, the first information can also be used to request filtering information, service experience information, and / or network energy consumption information, wherein the filtering information is used to indicate the scope of application of the policy.

[0212] Accordingly, in response to the first information, the second information may also include the service quality configuration policies for multiple terminal devices within the network or area.

[0213] Optionally, the second information may also include at least one of the following: validity period information, service experience information, and network energy consumption information.

[0214] Figure 7 A schematic diagram of a strategy determination device 500 is provided. This device includes a receiving unit 510 and a transmitting unit 520. The strategy determination device 500 can be a data analysis result subscriber device as described in the above method embodiments, or it can be a chip used to implement the functions of the data analysis result subscriber device as described in the above method embodiments.

[0215] In one possible design, the strategy determining device 500 can be implemented Figures 3 to 5 Any of the functions possessed by the data analysis results subscriber device in any of the embodiments shown in any of the figures.

[0216] For example, the sending unit 530 is used to send first information, which is used to request air interface access policies and / or user plane path selection policies of multiple terminal devices within the network or area; the receiving unit 510 is used to receive second information, which includes air interface access policies and / or user plane path selection policies of multiple terminal devices within the network or area; or, the receiving unit 510 is also used to receive an AI model, which is used to obtain air interface access policies and / or user plane path selection policies of multiple terminal devices within the network or area.

[0217] The first information is also used to request service quality configuration policies for multiple terminal devices within the network or the area.

[0218] Optionally, the first information can also be used to request filtering information, service experience information, and / or network energy consumption information, wherein the filtering information is used to indicate the scope to which the policy applies.

[0219] Accordingly, in response to the first information, the second information may also include the service quality configuration policies for multiple terminal devices within the network or area.

[0220] Optionally, the second information may also include at least one of the following: validity period information, service experience information, and network energy consumption information.

[0221] Figure 8 The structural block diagram of device 600 is determined according to the strategy provided in the embodiments of this application. Figure 8 The strategy determination device 600 shown includes a processor 610, a memory 620, and a communication interface 630. The processor 610 is coupled to the memory and is used to execute instructions stored in the memory to control the communication interface 630 to send and / or receive signals.

[0222] It should be understood that the processor 610 and memory 620 described above can be combined into a single processing device, with the processor 610 executing the program code stored in the memory 620 to achieve the aforementioned functions. In specific implementations, the memory 620 can be integrated into the processor 610 or independent of the processor 610.

[0223] In one possible design, the strategy determines that device 600 can be a data analysis device in the above method embodiments, or a chip used to implement the functions of the data analysis device in the above method embodiments.

[0224] Specifically, the strategy determining device 600 may correspond to the data analysis device in methods 100 to 300 according to embodiments of this application, and the strategy determining device 600 may include tools for performing... Figures 3 to 5The data analysis device in the device 600 is a unit that executes the method. Furthermore, this strategy determines that each unit in the device 600 and the other operations and / or functions described above are respectively for implementing the corresponding processes of methods 100 to 300. It should be understood that the specific process by which each unit executes the corresponding steps described above has been detailed in the above method embodiments, and for the sake of brevity, will not be repeated here.

[0225] When the strategy determines that device 600 is a chip, the chip includes a transceiver unit and a processing unit. The transceiver unit can be an input / output circuit or a communication interface; the processing unit can be a processor, microprocessor, or integrated circuit integrated on the chip. This application also provides a processing apparatus, including a processor and an interface. The processor can be used to execute the methods described in the above method embodiments.

[0226] It should be understood that the aforementioned processing device can be a chip. For example, the processing device can be a field-programmable gate array (FPGA), an application-specific integrated circuit (ASIC), a system-on-chip (SoC), a central processor unit (CPU), a network processor (NP), a digital signal processor (DSP), a microcontroller unit (MCU), a programmable logic device (PLD), or other integrated chips.

[0227] In implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software. The steps of the method disclosed in the embodiments of this application can be directly implemented by a hardware processor, or by a combination of hardware and software modules in the processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, detailed descriptions are omitted here.

[0228] It should be noted that the processor in the embodiments of this application can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiments can be completed by the integrated logic circuitry in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above methods.

[0229] It is understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous-link dynamic random access memory (SLDRAM), and direct memory bus RAM (DR RAM). It should be noted that the memory used in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0230] According to the method provided in the embodiments of this application, this application also provides a computer program product, which includes: computer program code, which, when run on a computer, causes the computer to execute... Figure 3 and Figure 5 The method of any one of the embodiments shown.

[0231] According to the method provided in the embodiments of this application, this application also provides a computer-readable medium storing program code, which, when run on a computer, causes the computer to perform... Figure 4 and Figure 8 The method of any one of the embodiments shown.

[0232] According to the method provided in the embodiments of this application, this application also provides a system that includes the aforementioned apparatus or device.

[0233] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0234] The terms “component,” “module,” “system,” etc., used in this specification are used to refer to computer-related entities, hardware, firmware, combinations of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, and / or a computer. As illustrated, applications running on computing devices and computing devices can both be components. One or more components may reside in a process and / or an execution thread, and components may be located on a single computer and / or distributed among two or more computers. Furthermore, these components can be executed from various computer-readable media on which various data structures are stored. Components can communicate, for example, via local and / or remote processes based on signals having one or more data packets (e.g., data from two components interacting with another component between a local system, a distributed system, and / or a network, such as the Internet interacting with other systems via signals).

[0235] It should also be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0236] It should also be understood that the use of numbers such as "first", "second", "#a", "#b", "#1", and "#2" in the embodiments of this application is only to distinguish different objects, such as different "information", "equipment manufacturers", "equipment", or "units". The understanding of specific objects and the correspondence between different objects should be determined by their functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0237] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0238] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0239] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0240] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0241] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0242] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0243] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method of policy determination, characterized by, The method comprises: obtaining first data and labels corresponding to the first data based on a digital twin, the first data being used to train an artificial intelligence (AI) model, and the AI model being used to obtain air interface access strategies and / or user plane path selection strategies of a plurality of terminal devices in a network or a region; training an AI model based on the first data and the labels corresponding to the first data.

2. The method of claim 1, wherein, The AI model is further used to obtain service quality parameter allocation strategies of the plurality of terminal devices in the network or the region.

3. The method according to claim 1 or 2, characterized in that, The method further comprises: obtaining second data from a data provider, wherein the data provider comprises an operation administration and maintenance (OAM) system, a network function (NF) network element, and a radio access network (RAN) network element; generating the digital twin based on the second data.

4. The method of claim 1, wherein, The method of obtaining the first data and the labels corresponding to the first data based on the digital twin comprises: obtaining the first data based on the digital twin; and obtaining the labels corresponding to the first data based on the first data and the digital twin.

5. The method according to claim 1 or 2, characterized in that, The first data comprises at least one of the following historical information of the plurality of terminal devices in the network or the region: location information, service information, reference signal received power (RSRP) information, reference signal received quality (RSRQ) information, and signal-to-interference-and-noise ratio (SINR) information.

6. The method of claim 3, wherein, The second data comprises at least one of the following information: topology information between network devices in the network or the region, connection information between terminal devices and network devices in the network or the region, device information or state information of the network devices, and device information or state information of the terminal devices.

7. The method of claim 6, wherein, The network devices comprise at least one of the following: a RAN network element, an access and mobility management function (AMF) network element, a session management function (SMF) network element, and a user plane function (UPF) network element.

8. The method of claim 7, wherein: the network devices comprise the RAN network element, the device information or the state information of the network devices comprises identity information and service area information of the RAN network element, and the device information or the state information of the terminal devices comprises RSRP, RSRQ, and SINR information of the plurality of terminal devices in the region; the network devices comprise the AMF network element, the device information or the state information of the network devices comprises identity information and service area information of the AMF network element, and the device information or the state information of the terminal devices comprises location information of the plurality of terminal devices in the region; the network devices comprise the SMF network element, the device information or the state information of the network devices comprises identity information and service area information of the SMF network element, and the device information or the state information of the terminal devices comprises service information of the plurality of terminal devices in the region; the network devices comprise the UPF network element, the device information or the state information of the network devices comprises identity information, service area information, quality of service (QoS) flow bandwidth information, packet loss rate, and latency information of the UPF network element.

9. A method of policy determination, characterized by, The method comprises: obtaining third data, the third data comprising at least one of the following current information of a plurality of terminal devices in a network or a region: location information, service information, reference signal received power (RSRP) information, reference signal received quality (RSRQ) information, and signal-to-interference-and-noise ratio (SINR) information; inputting the third data into an artificial intelligence (AI) model to obtain air interface access strategies and / or user plane path selection strategies of the plurality of terminal devices in the network or the region, the AI model being trained by the method of any one of claims 1 to 8.

10. The method of claim 9, wherein, The method further comprises: obtaining a service quality parameter allocation strategy of the plurality of terminal devices in the network or the region.

11. The method according to claim 9 or 10, characterized in that, The method is performed by a network data analysis network element, and the obtaining of the third data comprises: obtaining the third data from a data provider, wherein the data provider comprises an operation administration and maintenance (OAM) system, a network function (NF) network element, and a radio access network (RAN) network element; or obtaining the third data according to first data, wherein the first data comprises at least one of the following historical information of the plurality of terminal devices in the network or the region: location information, service information, reference signal received power (RSRP) information, reference signal received quality (RSRQ) information, and signal-to-interference-and-noise ratio (SINR) information.

12. The method of claim 9 or 10, wherein, When the method is performed by a network data analysis network element, the method further comprises: receiving first information for requesting air interface access strategies and / or user plane path selection strategies of the plurality of terminal devices in the network or the region; sending second information comprising the air interface access strategies and / or the user plane path selection strategies of the plurality of terminal devices in the network or the region; or sending the AI model.

13. The method of claim 12, wherein, The first information is further used to request a service quality configuration strategy of the plurality of terminal devices in the network or the region.

14. The method of claim 12, wherein, The first information is further used to request screening information, service experience information, and / or network energy consumption information, wherein the screening information is used to indicate a range to which the strategy is applicable.

15. The method of claim 12, wherein, The second information further comprises a service quality configuration strategy of the plurality of terminal devices in the network or the region.

16. The method of claim 12, wherein, The second information further comprises at least one of the following information: validity period information, service experience information, and network energy consumption information.

17. A method of policy determination, characterized by, comprises: sending first information for requesting air interface access strategies and / or user plane path selection strategies of a plurality of terminal devices in a network or a region; receiving second information comprising the air interface access strategies and / or the user plane path selection strategies of the plurality of terminal devices in the network or the region, the air interface access strategies and / or the user plane path selection strategies of the plurality of terminal devices in the network or the region being obtained based on an AI model, the AI model being trained by the method of any one of claims 1 to 8; or receive an AI model, the AI model being used to obtain air interface access strategies and / or user plane path selection strategies of a plurality of terminal devices within the network or the area, the AI model being trained by the method of any one of claims 1 to 8.

18. The method of claim 17, wherein, The first information is further used to request service quality configuration strategies of a plurality of terminal devices within the network or the area.

19. The method of claim 17 or 18, wherein, The first information is further used to request filtering information, service experience information, and / or network energy consumption information, wherein the filtering information is used to represent a range to which the strategies are applicable.

20. The method of claim 17, wherein, The second information further comprises service quality configuration strategies of a plurality of terminal devices within the network or the area.

21. The method of claim 17 or 18, wherein, The second information further comprises at least one of the following information: validity period information, service experience information, and network energy consumption information.

22. A policy determination apparatus characterized by comprising: comprise: a memory for storing a computer program; a processor for executing the computer program stored in the memory, so that the apparatus executes the method of any one of claims 1 to 8, or so that the apparatus executes the method of any one of claims 9 to 16.

23. A computer-readable storage medium, characterized in that, The computer program is stored on the computer readable storage medium, and when the computer program runs, causes an apparatus to execute the method of any one of claims 1 to 8, or causes an apparatus to execute the method of any one of claims 9 to 16.

24. A communication system comprising a data analytics network element for performing the method of any one of claims 1 to 16, and a core network element in communication with the data analytics network element.

25. A chip system, characterized by comprise: a processor for calling and running a computer program from a memory, so that a communication apparatus installed with the chip system executes the method of any one of claims 1 to 8; or so that a communication apparatus installed with the chip system executes the method of any one of claims 9 to 16.

Images