Service verification method and device

Abstract

The invention relates to the technical field of communication, in particular to a service verification method and device, and aims to guarantee the efficiency and accuracy of service verification and improve the range of service verification through a virtual-real combination mode of a digital twin network and a physical twin network. The method comprises the following steps: acquiring a service verification request, wherein the service verification request comprises a service demand of a network service; according to the service verification request, a verification environment corresponding to the network service is configured based on a digital twin network and a physical twin network corresponding to the physical network; obtaining a verification result of the network service, wherein the verification result is determined by verifying the service capability of the network service in the verification environment; wherein the verification environment comprises a first verification environment constructed based on a digital twin network and a second verification environment constructed based on a physical twin network; alternatively, the verification environment is constructed based on at least one digital twin function network element in the digital twin network and at least one physical twin function network element in the physical twin network.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a service verification method and apparatus. Background Technology

[0002] As the core network structure becomes increasingly complex, the innovation cycle of network services based on the core network becomes longer, and the reliability of newly launched network services becomes increasingly difficult to guarantee. Furthermore, with the gradual maturation of network intelligence, a large number of new network services will emerge. Therefore, how to quickly verify network services and achieve secure deployment is a pressing issue that needs to be addressed.

[0003] Currently, one approach to service verification is to utilize digital twin technology to establish digital twin functional network elements (i.e., models) for each network element in the actual core network (i.e., the actual physical network), thus constructing a digital twin network for the actual core network. The data twin network can be understood as a mirrored virtual network of the actual core network. A verification environment for network services is configured based on the data twin network to verify these services. The verification results based on the digital twin network can be directly applied to the actual core network. For example, if the verification results for the network services meet expectations, then the network services can be applied to the actual core network.

[0004] However, data twin networks struggle to fully simulate the actual core network. Directly applying the verification results of data twin networks to the actual core network fails to meet the high reliability requirements of the core network. Furthermore, for network services that introduce new network elements, digital twin networks lack data on these new elements, making it difficult to construct accurate models and obtain high-precision verification results. Summary of the Invention

[0005] This application provides a service verification method and apparatus, which aims to perform service verification through a combination of digital twin network and physical twin network, thereby ensuring the efficiency and accuracy of service verification and expanding the scope of service verification.

[0006] Firstly, embodiments of this application provide a service verification method. This method can be executed by a network digital twin function (NDTF). Here, NDTF can refer to the NDTF itself, or to the components within the NDTF that implement this method (such as processors, modules, chips, or chip systems), or to logical modules or software capable of implementing all or part of the NDTF functions (such as the NDTF control plane, i.e., the network digital twin control function (NDTF-C)). Taking the execution of this method by the NDTF as an example, the method includes: obtaining a service verification request, the service verification request including the service requirements of the network service; configuring a verification environment corresponding to the network service based on the digital twin network and the physical twin network corresponding to the physical network according to the service verification request; obtaining the verification result of the network service, the verification result being determined by verifying the service capabilities of the network service in the verification environment; wherein, the verification environment includes a first verification environment constructed based on the digital twin network and a second verification environment constructed based on the physical twin network; or, the verification environment is constructed based on at least one digital twin function network element in the digital twin network and at least one physical twin function network element in the physical twin network.

[0007] In this embodiment, NDTF can verify network services using a hybrid approach of digital twin and physical twin, combining the accuracy guarantee of physical twin network verification with the efficiency advantages of digital twin network verification. This ensures the efficiency and accuracy of service verification, and the verification process has no impact on the actual physical network. Furthermore, the physical twin network can be used to support newly introduced network elements (e.g., the function of the new network element is implemented by the corresponding physical twin functional network element in the physical twin network), supporting the verification of various network services, including those with newly introduced network elements, thus expanding the scope of service verification.

[0008] In one possible design, the service verification request includes first information, which instructs the service verification to perform function offloading or data offloading; wherein, function offloading can also be referred to as network element function offloading or network element offloading. If the first information instructs the service verification to perform function offloading, the verification environment is constructed based on at least one digital twin functional network element in the digital twin network and at least one physical twin functional network element in the physical twin network; if the first information instructs the service verification to perform data offloading, the verification environment includes a first verification environment constructed based on the digital twin network and a second verification environment constructed based on the physical twin network.

[0009] The above design allows for the selection of traffic splitting methods as needed, meeting the verification requirements of different network services. Specifically, functional traffic splitting increases the focus of verification and saves resources; data traffic splitting allows for dynamic traffic splitting according to different scenarios, enabling verification of network services of varying scales and providing greater flexibility.

[0010] In one possible design, the first information instructs the service verification to perform functional offloading, and the service verification request also includes second information, which instructs at least one physical twin functional network element to perform functional offloading in the physical twin network; according to the service verification request, the verification environment corresponding to the network service is configured in the digital twin network and the physical twin network, including: determining multiple network elements on which the network service depends according to the service verification request; and configuring the verification environment according to the multiple network elements on which the network service depends and the second information.

[0011] The above design allows for on-demand function offloading and increases the focus of verification. The network elements to be verified rely on the implementation of physical twin functional network elements rather than digital twin functional network elements, which can avoid the error between digital twin functional network elements and actual network elements and improve the reliability of service verification.

[0012] In one possible design, it further includes: obtaining data characteristics of service messages corresponding to network services from physical networks and / or physical twin networks; generating simulated service messages based on the data characteristics; and verifying the service capabilities of network services in a verification environment, including: verifying the service capabilities of network services in a verification environment by simulating service messages.

[0013] With the above design, the verification process is not directly driven by actual data in the physical network, which can avoid data leakage in the physical network and the resulting security risks.

[0014] In one possible design, the verification environment includes a first verification environment built on a digital twin network and a second verification environment built on a physical twin network. The method further includes: determining a data diversion strategy for simulated business messages in the first and second verification environments; and diverting simulated business messages to the first and second verification environments according to the data diversion strategy.

[0015] Through the above design, simulated message data can be distributed according to a certain data distribution strategy, and the business volume of the first verification environment and the second verification environment can be flexibly controlled.

[0016] In one possible design, the simulated service message is diverted to the first verification environment and the second verification environment according to the data diversion strategy, including: sending the data diversion strategy to the service distribution function network element, the data diversion strategy being used by the service distribution function network element to divert the simulated service message to the first verification environment and the second verification environment.

[0017] Through the above design, the service distribution function network element can simulate the distribution of service messages, which helps to improve the accuracy of simulated service message distribution and avoids interference with the actual physical network.

[0018] In one possible design, the method further includes: acquiring first running data corresponding to a first verification environment and second running data corresponding to a second verification environment; determining the deviation of the first verification environment relative to the second verification environment based on the first running data and the second running data; and adjusting the first verification environment based on the deviation.

[0019] Through the above design, by comparing the business simulation processes of the first verification environment built on a data twin network and the second verification environment built on a physical twin network, the verification process can be improved in real time, thereby increasing the accuracy of business verification.

[0020] In one possible design, the business requirements include at least one business indicator of the network service, and obtaining the verification result of the network service includes: obtaining the verification result of at least one business indicator; and determining the verification result of the network service based on the verification result of at least one business indicator.

[0021] Through the above design, the verification result of network services can be determined based on the verification result of at least one service indicator of the network service, which is beneficial for the network service verification requester to know the simulation operation status of various service indicators of the network service.

[0022] Secondly, embodiments of this application provide a communication device that has the function of implementing the method described in the first aspect. This function can be implemented in hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above-described function, such as an interface unit and a processing unit.

[0023] In one possible design, the device can be a chip or an integrated circuit.

[0024] In one possible design, the device includes a memory and a processor, the memory for storing instructions executed by the processor, and when the instructions are executed by the processor, the device can perform the method of the first aspect.

[0025] Thirdly, embodiments of this application provide a communication device including an interface circuit and a processor, wherein the processor and the interface circuit are coupled to each other. The interface circuit is used for inputting and / or outputting signals, and the processor is used to implement the method described in the first aspect through logic circuits or executing instructions. It is understood that the interface circuit can be a transceiver, a transceiver device, or an input / output interface.

[0026] Optionally, the communication device may also include a memory for storing instructions executed by the processor, or storing input data required by the processor to execute instructions, or storing data generated after the processor executes instructions. The memory may be a physically independent unit, or it may be coupled to the processor, or the processor may include the memory (i.e., the processor and the memory are integrated together).

[0027] In one possible implementation, the communication device is a chip.

[0028] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program or instructions, which, when executed by a processor, can implement the method described in the first aspect.

[0029] Fifthly, embodiments of this application also provide a computer program product, including a computer program or instructions, which, when executed by a processor, can implement the method described in the first aspect.

[0030] In a sixth aspect, embodiments of this application also provide a chip system including a processor, which is coupled to a memory for storing programs or instructions. When the program or instructions are executed by the processor, the method described in the first aspect can be implemented.

[0031] The technical effects achievable by the second to sixth aspects mentioned above are similar to those achievable by the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0032] Figure 1 This is a schematic diagram of the network architecture provided in the embodiments of this application;

[0033] Figure 2 A schematic diagram of physical twin network verification technology provided in the embodiments of this application;

[0034] Figure 3 A schematic diagram illustrating the network service innovation process and time overhead provided in the embodiments of this application;

[0035] Figure 4 This is a schematic diagram of data twin network verification provided in an embodiment of this application;

[0036] Figure 5This is a schematic diagram of a virtual-real fusion twin verification architecture provided in an embodiment of this application;

[0037] Figure 6 A schematic diagram of the business verification method provided in the embodiments of this application;

[0038] Figure 7 and Figure 8 This is a schematic diagram of the business verification process provided in the embodiments of this application;

[0039] Figure 9 A schematic diagram of the network twin verification logic architecture that integrates virtual and real elements provided in this application embodiment;

[0040] Figure 10 and Figure 11 This is a schematic diagram of the structure of the communication device provided in the embodiments of this application. Detailed Implementation

[0041] This application provides a business verification method and apparatus. The method and apparatus are based on the same inventive concept. Since the principles by which the method and apparatus solve the problem are similar, their implementations can be mutually referenced, and repeated details will not be elaborated further.

[0042] The technical solutions of this application can be applied to various communication systems, such as 5th generation (5G) communication systems, 5G-advanced (5G-A) communication systems, and future communication systems. The following describes some network architectures to which this application applies. In the following description, the terminal device is taken as a user equipment (UE).

[0043] like Figure 1The diagram illustrates a possible 5G network architecture applicable to this application. This 5G network architecture includes a UE, a data network (DN), and an operator network. The operator network may include one or more of the following network elements (or devices): access network (AN) equipment or radio access network (RAN) equipment, user plane function (UPF) network elements, authentication server function (AUSF) network elements, access and mobility management function (AMF) network elements, session management function (SMF) network elements, network function repository function (NRF) network elements, network slice selection function (NSSF) network elements, network exposure function (NEF) network elements, network data analytics function (NWDAF) network elements, policy control function (PCF) network elements, user data management (UDM) network elements, and application function (AF) network elements, etc. In the aforementioned operator networks, network elements or equipment other than access network equipment (such as AN equipment or RAN equipment) can be referred to as core network elements or core network equipment.

[0044] It is necessary to understand that Figure 1 The network elements / devices involved can be deployed in one or more forms. These network elements can also be referred to as entities or network functions (NFs). The aforementioned UPF, AMF, and SMF network elements can also be referred to as UPF, AMF, SMF, etc.

[0045] Terminal equipment: Terminal equipment communicates with access network equipment using some kind of air interface technology. This air interface can be a 5G-based wireless air interface, such as New Radio (NR); or it can be an air interface based on the next-generation mobile communication network technology standard based on 5G; or it can be an air interface based on 4G standards (such as the Long Term Evolution (LTE) system), etc. Terminal equipment can be user equipment (UE), handheld terminals, laptops, subscriber units, cellular phones, smartphones, wireless data cards, personal digital assistant (PDA) computers, tablet computers, wireless modems, handheld devices, laptop computers, cordless phones, machine type communication (MTC) terminals, or other devices that can access the network.

[0046] Access network equipment is primarily responsible for functions such as radio resource management, quality of service (QoS) management, data compression, and encryption on the air interface side. Access network equipment can be base stations, pole-mounted stations, integrated access and backhaul (IAB) nodes, Node Bs, mobile base stations, evolved NodeBs (eNodeBs), transmission reception points (TRPs), radio access networks, radio access network equipment, evolved NodeBs (eNodeBs) in LTE systems or evolved LTE-A systems, next-generation NodeBs (gNBs) in 5G mobile communication systems, and base stations in future mobile communication systems. It can also be modules or units that perform some of the functions of a base station; for example, it can be a central unit (CU) or a distributed unit (DU). Radio access network equipment can be macro base stations, micro base stations (also called small stations), indoor stations, relay nodes, or donor nodes. The embodiments of this application do not limit the specific technology or specific device form used in the access network equipment.

[0047] In addition, access network equipment can also be untrusted non-3GPP access network equipment. Untrusted non-3GPP access network equipment can allow terminal equipment and the 3GPP core network to interconnect using non-3GPP technologies, such as Wireless Fidelity (Wi-Fi), Worldwide Interoperability for Microwave Access (WiMAX), and Code Division Multiple Access (CDMA) networks.

[0048] AF (Application Provider): Primarily responsible for relaying application-side requests to the network side. AF can be a third-party functional entity or an application service deployed by the operator.

[0049] UDM: Primarily responsible for contract data management and user access authorization.

[0050] PCF: Primarily responsible for policy control, including session and service flow-level billing, QoS bandwidth guarantee and mobility management, and UE policy decision-making.

[0051] NWDAF (Network Node-Driven Application): Primarily responsible for network data collection, logical analysis, result subscription, artificial intelligence (AI) inference, AI training, and model management. It acquires relevant data from the core network, trains network models, predicts the network's future, and feeds back analysis reports to NFs (Network Elements or Network Functions) subscribers to achieve an intelligent closed loop. As the center of intelligent decision-making in the core network, it uses AI inference for network optimization and user experience improvement.

[0052] NEF: Primarily responsible for exposing network resources to external applications, including the ability to provide network resources to third-party applications.

[0053] NSSF: Primarily responsible for network path selection, thereby improving network performance and user experience. Simultaneously, it can allocate different network bandwidths and resources to different traffic types according to user needs and priorities, achieving optimized utilization of network resources.

[0054] AUSF: Primarily responsible for authentication service functions. For example, it is responsible for authenticating 3GPP and non-3GPP access.

[0055] AMF: Primarily responsible for mobility management, access authentication / authorization, and user policy delivery.

[0056] SMF: Primarily responsible for PDU session management, PCF control policy execution, UPF selection, and UE Internet Protocol (IP) address allocation.

[0057] NRF: Primarily responsible for storing and managing network entity information, allocating network resources, and coordinating the deployment of network functions and services.

[0058] UPF: Primarily responsible for acting as the interface with the data network, performing user plane data forwarding, session / flow-level billing statistics, bandwidth limiting, etc.

[0059] Figure 1 N1, N2, N4, Nausf, Namf, etc., are interface names or serial numbers. For example, the meanings of the above interface names or serial numbers can be found in the definitions in the 3GPP standard protocol.

[0060] It should be understood that the network elements in the core network (CN) can be network components implemented on dedicated hardware, software instances running on dedicated hardware, or instances of virtualized functions on a virtualization platform (such as a cloud platform). This application does not limit the distribution of the network elements in the communication system. Optionally, the network elements can be deployed in different physical devices, or multiple network elements can be integrated into the same physical device.

[0061] The embodiments of this application do not limit the names of each network element in the communication system. For example, in communication systems of different standards (or access technologies), each network element may have other names; for another example, when multiple network elements are integrated into the same physical device, the physical device may also have other names.

[0062] To facilitate understanding by those skilled in the art, some terms used in this application are explained below.

[0063] 1) Network physical twin.

[0064] A network physical twin is similar to a small-scale mirror image of a network. Its constituent entities are the same as the physical entities of the actual network, and the only difference between them is the topology and the number of users they can support. All other physical and software configurations are consistent with the actual network.

[0065] 2) Physical twin technology.

[0066] In the process of business innovation in network services, a significant portion of the time is spent building complex network verification environments. Therefore, to save time in setting up these verification environments, a physical twin network verification environment can be pre-built. Once the new network service is developed, a certain percentage of actual users can be diverted to the physical twin network to quickly complete the verification of the new service.

[0067] Reference Figure 2 The diagram shown illustrates the physical twin network verification technology. A physical twin network is similar to a small-scale mirror of an actual physical network (such as a large commercial network). Its constituent entities (such as network elements) are the same as the physical entities of the actual network. Its capabilities and services are consistent with the actual physical network. The only difference between the physical twin network and the actual physical network is the topology scale and the number of users it can carry. All other hardware and software configurations are consistent with the actual network.

[0068] 3) Digital twin technology.

[0069] Digital twin is a technology that uses digital models to simulate and analyze real-world physical entities or systems in real time. It connects the real world with the digital world by collecting real-time data from physical entities, allowing for the testing of realistic scenarios in a virtual space. The fundamental principle of digital twins is to fully utilize data from physical models, sensors, and operational history, integrating multi-disciplinary, multi-physical-quantity, multi-scale, and multi-probabilistic simulation processes to complete mapping in virtual space, thereby reflecting the entire lifecycle of the corresponding physical equipment. Digital twin technology can help companies optimize, simulate, and test in a virtual environment before actual production, ultimately achieving efficient flexible production, rapid innovation, and market launch.

[0070] Digital twin technology, which has recently seen significant development and promotion, is essentially a virtual model of a physical object. It simulates and monitors the operation of the physical object using real-time data, thus achieving a virtual replica of the real-world object. Digital twin technology can replicate many real-world items, from small factory equipment and test fans to large-scale industrial parks and even cities, enabling real-time monitoring of physical operations, identification of potential risks, and assistance for human decision-making.

[0071] The difference between digital twins and physical twins lies in their real-time performance and scalability. Physical twins are often used in the design phase for design verification, while digital twins are mainly used for real-time physical mapping to reflect the actual physical operation. In addition, physical twins are often limited in scale, while the pure virtualization approach of digital twins can perform simulations and modeling on a much larger scale.

[0072] 4) Data aspect.

[0073] The data plane is analogous to the control plane and user plane in the 5G core network. It is a collection dedicated to carrying out data acquisition, transmission and storage functions in the core network. It includes unified data processing capabilities such as data acquisition methods, data protocols, data transmission channels, data subscription, data storage, data conversion and data security.

[0074] 5) In the description of this application, terms such as "first" and "second" are used only to distinguish multiple objects and are not used to limit the size, content, order, timing, priority, or importance of multiple objects. For example, the first hop count indication information and the second hop count indication information do not indicate a difference in priority or importance between the two hop count indication information.

[0075] 6) In the embodiments of this application, the number of nouns, unless otherwise specified, refers to "singular nouns or plural nouns," that is, "one or more." "At least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, or B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the related objects before and after are in an "or" relationship. For example, A / B means: A or B. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c means: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0076] Core network services generally need to be jointly carried by multiple network elements. The corresponding network services are completed through multiple interactions between network elements. Different network element entities have different deployment locations, number of entities, and linkage and coordination according to different network service needs, resulting in high overall complexity. This is especially true under complex and diverse network service requirements, which then manifest in various ways.

[0077] Taking the user session establishment process as an example, the procedure is as follows: The terminal device (such as the UE) sends a session establishment request to the AMF through the RAN. The AMF queries the corresponding NRF, obtains the registered SMF information, selects the corresponding SMF to provide session services, saves the mapping relationship between the SMF and PDU sessions, and forwards the session establishment request to the SMF. The SMF selects the appropriate UPF for the UE, establishes a user plane transport path, and allocates an IP address. During this process, the SMF also initiates a policy control session establishment request to the PCF, establishes a policy control session between the SMF and the PCF, and saves the association between the policy control session and the PDU session. Finally, it returns a complete session establishment request to the UE.

[0078] As core network structures become increasingly complex, the innovation cycle for network services based on the core network lengthens, making it more difficult to launch new network service capabilities and ensure reliability. In the future, with the gradual maturation of network intelligence, a large number of new network services will emerge. How to quickly achieve zero-risk and secure deployment of these new network services is a pressing issue that needs to be addressed.

[0079] Reference Figure 3 The diagram illustrates the network service innovation process and time overhead. Network service innovation includes four main stages: new service construction, new service process verification, new service pilot operation, and large-scale commercial application of the new service. It further includes several smaller stages such as function development and network element integration. Figure 3 It is known that it takes more than a year for a new network service to go from development completion to trial commercial use, and nearly two years for large-scale commercial delivery. The high-risk nature and impact of core network services make the delivery of new network services extremely cautious, with a longer cycle time and higher reliability requirements compared to other product services. This, to some extent, limits the rapid development of core network services.

[0080] Currently, service verification for network operations typically utilizes digital twin technology to create a real-time digital twin simulation of the core network. This usually involves establishing an independent network digital twin or digital twin layer. Through real-time mapping between the digital twin layer and the actual physical network, a fully mirrored virtual network is formed at the data twin layer—that is, a data twin network mapped to the actual physical network. Furthermore, all modifications to be applied to the actual core network can be pre-verified based on the network digital twin layer.

[0081] like Figure 4 The diagram illustrating data twin network verification shows that network applications and the actual physical network (such as the core network) are linked through a network digital twin layer. For new network services in network applications, an intent request is sent to the digital twin layer. The digital twin layer models and digitally simulates the new network service or network element, constructing a virtual service implementation. Simultaneously, it obtains the corresponding data flow and user flow from the actual physical network environment in real time, applying them to the virtual network service implementation and performing corresponding simulation verification. When the simulation verification results meet the requirements, the new network service can be applied to the actual physical network (depending on the new service scenario, corresponding upgrades to the actual physical network may be required).

[0082] However, data twin networks struggle to fully simulate the actual core network. Directly applying the verification results of data twin networks to the actual core network fails to meet the high reliability requirements of the core network. Furthermore, for network services that introduce new network elements, digital twin networks lack data on these new elements, making it difficult to construct accurate models and obtain high-precision verification results.

[0083] Based on this, embodiments of this application provide a service verification method and apparatus, aiming to perform service verification through a combination of digital twin and physical twin networks, thereby ensuring the efficiency and accuracy of service verification, expanding the scope of service verification, and enabling service verification for network services that introduce new network elements. The embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0084] Figure 5 This is a schematic diagram of a virtual-physical twin verification architecture provided in an embodiment of this application. The verification architecture includes an actual physical network (such as an actual core network), a physical twin network corresponding to the actual physical network, and a digital twin network.

[0085] The Network Digital Twin Function (NDTF), acting as a digital twin platform or an independent network element, provides the capabilities of a digital twin network. It can be further broken down into the Control Function of Network Digital Twin (NDTF-C) and the Execution Function of Network Digital Twin (NDTF-E). NDTF (or NDTF-C and NDTF-E) can interoperate with other network elements under other 5G protocols based on a Service-Based Interface (SBI).

[0086] NDTF and NRF Interaction: NDTF can connect to NRF, register its functions with NRF, and provide network digital twin services. Then, when other network elements need to use the digital twin service of NDTF, they can request NRF to find the corresponding NDTF (or NDTF-C).

[0087] NDTF and NWDAF Interaction: NDTF can interact with NWDAF. NWDAF generates intelligent policies or intelligent control commands through intelligent inference. The intelligent policies and control commands generated by NWDAF can be validated by calling NDTF to assess the feasibility and impact of the intelligent results. Simultaneously, when training for certain business scenarios, NWDAF can also request NDTF to generate simulated data as training data augmentation to enhance the correctness of NWDAF training. NDTF and NWDAF can be independent or mutually inclusive.

[0088] Interaction between NDTF and Service Distribute Function (SDF): Here, SDF is a functional entity responsible for message routing and connection scheduling. In this embodiment, SDF has independent simulated data routing capabilities. Its execution entity needs to be separated from the routing entity of the designed physical network to avoid excessive verification data flow routing (such as simulated service message routing) affecting the actual physical network's message routing. Verification messages and data generated by NDTF-E simulation can be routed between the digital twin network and the physical twin network via SDF. Essentially, simulated verification messages (such as simulated service messages) are sent to NFs (Network Elements) in both the NDTF-E and physical twin networks according to the routing strategy generated by NDTF-C. This routing strategy can be dynamically adjusted based on verification needs, with NDTF-C responsible for generating and distributing the strategy.

[0089] Interaction between NDTF and other Network Elements (NFs): In verification scenarios, the interaction between NDTF and NFs mainly involves subscribing to the data features or non-sensitive raw data of the NFs. As the NFs operate, the subscribed NFs need to provide corresponding data or data features on demand. These data features include, but are not limited to, the type of data message, the network element information, the data network name (DNN) information, the network slicing (NS) information, data structure information, data stream size, the frequency of similar data streams, the user type and generation ratio of different data, etc. These data features can characterize the structure and dynamic characteristics of the data itself from multiple dimensions. Therefore, NDTF can generate similar simulated data through learning and inference, and generate corresponding verification message simulations based on the dynamic changes of the data. NDTF's learning and inference capabilities can be achieved by leveraging external intelligent functional agents such as NWDAF, or it can possess these capabilities itself; the method of achieving these capabilities is not limited in this application.

[0090] NDTF and Data Plane Interaction: The data plane is a carrier for data storage and transmission. The twin model required by NDTF, temporary verification data, result data, etc. can all be stored and retrieved in the data plane, including execution context information. The data plane can be a collection of states of different network element functional bodies and a collection of data, enabling the statelessness of network elements. NDTF can also be combined with the data plane to establish stateless NDTF services.

[0091] NDTF can be deployed as needed based on network service requirements. For sites with innovative network service needs, it is advisable to consider deploying NDTF to achieve rapid and reliable verification of new services.

[0092] The service scenarios provided in this application embodiment can be used for the verification of new network services in the core network. The new network services in the core network can include two major categories of scenarios: (1) network service verification from external operators or network service verification from connection domains outside the core network; (2) network service verification from within the core network, which can include service verification of various maintenance scenarios of the core network, service verification of new network element features, service verification of intelligent decision-making scenarios, etc.

[0093] Furthermore, the naming of the aforementioned network elements is defined solely for the purpose of distinguishing different functions and should not constitute any limitation on this application. This application does not preclude the possibility of using other names in 5G networks and other future networks. For example, in future networks, some or all of the aforementioned network elements may retain the terminology used in 5G, or they may adopt other names. For instance, NDTF or NDTF-C may also adopt other names in future networks.

[0094] The service verification method provided in this application can be executed by the NDTF. If the NDTF is broken down into NDTF-C and NDTF-E, it can also be executed by NDTF-C. It is understood that NDTF (or NDTF-C) can refer to the NDTF (or NDTF-C) itself, or to the components (such as processors, modules, chips, or chip systems) in the NDTF (or NDTF-C) that implement the method, or to logic modules or software that can implement all or part of the functions of the NDTF (or NDTF-C). The following uses the execution of the service verification method by NDTF-C as an example to introduce the service verification method provided in this application.

[0095] Figure 6 This is one of the schematic diagrams of a business verification method provided in an embodiment of this application. The method includes:

[0096] S601: NDTF-C obtains service verification request. The service verification request includes the service requirements of the network service.

[0097] In this embodiment, network services can be any type of network service, such as session service services, networking services, services to expand network coverage, or services to increase network speed, etc. The service requirements of a network service can also be understood as the service requirements or objectives of the network service, and these requirements may include at least one service indicator of the network service.

[0098] For example: If the network service is a session service, the service verification request may include service requirements such as supporting 1000 users to provide session services simultaneously, with a session initiation success rate of not less than 99.99% and a session establishment latency of not more than 100ms; or if the network service is a networking service, the service verification request may include service requirements such as supporting 1000 users to use the network simultaneously, with a network speed of not less than 1000Mbps, etc.

[0099] It is understandable that different network services may have different business requirements, and the specific business requirements are set by the business verification requester (such as the user) according to actual needs.

[0100] In one possible implementation, the business verification request may also include one or more of the following: verification count, verification resources (such as bandwidth). It is understood that if the business verification request does not indicate the verification count or verification resources, the NDTF-C may determine these parameters.

[0101] S602: NDTF-C configures the verification environment corresponding to the network service based on the digital twin network and physical twin network corresponding to the physical network, according to the service verification request.

[0102] The verification environment includes a first verification environment built on a digital twin network and a second verification environment built on a physical twin network; or, the verification environment is built on at least one digital twin functional network element in the digital twin network and at least one physical twin functional network element in the physical twin network.

[0103] In the embodiments of this application, digital twin network and physical twin network can refer to the digital twin network and physical twin network corresponding to the actual physical network (such as the core network) used by network services.

[0104] As an example: The network service is a session service, applied to the core network. A digital twin network can refer to a digital twin network generated for this core network using digital twin technology. This digital twin network can include digital twin functional network elements corresponding to each network element in the core network. The digital twin functional network element corresponding to any network element can be composed of a model representing that network element, or multiple models representing parts of the functions of that network element. A physical twin network can be understood as a small-scale mirror of the core network. Its constituent physical twin functional network elements are the same as those in the actual network, differing only in topology and the number of users carried; other hardware and software configurations remain consistent with the actual network.

[0105] In this embodiment, different traffic splitting methods can be used for service verification, such as data splitting or function splitting, thereby enabling network service verification through a combination of digital twin and physical twin networks. The choice between data splitting and function splitting can be determined by the NDTF-C or indicated by the service verification request. For example, the service verification request may include first information indicating whether service verification should be performed using function splitting or data splitting. The NDTF-C can determine whether to use data splitting or function splitting based on this first information.

[0106] For function offloading, NDTF-C can generate function offloading strategies. These strategies can split network elements within a network service process, executing some functions in the digital twin network and others in the physical twin network to achieve virtual-physical fusion verification. For data offloading, NDTF-C can generate data offloading strategies. Data offloading can separate service messages (or simulated service messages) into two parts: one part is offloaded to the digital twin network (or a first verification environment built on the data twin network), and the other part is offloaded to the physical twin network (or a second verification environment built on the physical twin network) to achieve virtual-physical fusion verification. The function offloading and data offloading strategies are explained below.

[0107] Functional offloading strategy: Generally, network services require multiple network elements to carry them, and these elements need to cooperate to complete a full service process. For example, session services require AMF, NRF, SMF, UPF, etc. Therefore, to verify a network service process, the network elements within the process can be functionally offloaded. Some functions are executed in the digital twin network, while others are executed in the physical twin network, achieving virtual-physical fusion verification. This offloading method is suitable for verifying the functionality of a specific network element, allowing for service function verification with minimal resource cost. For example, if a new network service process primarily handles the AMF, but the overall process involves interactions between existing AMF messages and PCF, SMF, etc., and direct physical verification is desired for accurate service verification, the AMF execution function of the new network service process can be offloaded to the physical twin network, while other PCF and SMF execution functions are offloaded to the digital twin network. This makes the AMF execution results of the new network service more illustrative.

[0108] Data offloading strategy: The typical characteristic of network services is that they are centered on user data. All related network element processing depends on user data parameters, such as subscription permanent identifier (SUPI), international mobile subscriber identity (IMSI), international mobile equipment identity (IMEI), network slicing (NS), or protocols. Similar data information is cached in the execution context of each network element. Through the exchange and processing of different data, the data is continuously processed according to business needs to generate new data results. Differences in the processing will produce different data results. Digital twin simulation uses a digital model to replace the actual running entity to generate data results. The more accurate the digital model is, the smaller the difference between it and the actual running entity. Therefore, NDTF-C can also split the test business messages (or simulated business messages) according to the needs of scenario verification. A portion is split into the digital twin network and another portion into the physical twin network. The splitting ratio can be adjusted as needed. For example, 99% of the simulated business messages generated in one iteration can be sent to the digital twin network and 1% to the physical twin network. This splitting can be done in various ways, such as sampling proportional splitting, where 99 out of every 100 messages are sent to the digital twin network and 1 out of every 100 messages is sent to the physical twin network, with each 100 messages forming a cycle; or, in one iteration, a total of 10,000 messages are sent, with the first 9,900 messages sent to the digital twin network and the last 100 messages sent to the physical twin network, and so on, in an iterative cycle.

[0109] After receiving a service verification request, NDTF-C can determine the network elements that the service verification depends on (or requires), generate a traffic splitting strategy (such as a function splitting strategy or a data splitting strategy), and thus configure the verification environment for network services.

[0110] As an example: the service requirements of the network service indicated by the service authentication request are: providing session services to 1000 users simultaneously, with a session initiation success rate of no less than 99.99% and a session establishment latency of no more than 100ms, etc. NDTF-C can determine that the network service is a session service service. The network elements that the service authentication depends on include AMF, NRF, SMF, and UPF, which are used to provide session services. The correspondence between each network service and its dependent network elements can be pre-configured. After receiving the service authentication request, NDTF-C can determine the network elements that the service authentication depends on based on the network service corresponding to the service authentication request and the correspondence between each network service and its dependent network elements.

[0111] Taking the NDTF-C function offloading strategy as an example, the generated function offloading strategy can place the functions of network elements such as NRF, SMF, and UPF in the digital twin network, and place the functions of AMF in the physical twin network.

[0112] Taking the NDTF-C-generated data offloading strategy as an example, the generated data offloading strategy can offload 90% of business messages (or simulated business messages) to the digital twin network (i.e., the first verification environment built on the data twin network) and 10% to the physical twin network (i.e., the second verification environment built on the physical twin network).

[0113] Taking the network elements that business verification depends on (or requires) including AMF, NRF, SMF, and UPF, function offloading is performed. The function offloading strategy is to execute the functions of network elements such as NRF, SMF, and UPF in the digital twin network, and execute the functions of AMF in the physical twin network. For example, NDTF-C can call the digital twin function network elements in the digital twin network corresponding to NRF, SMF, and UPF, and the physical twin function network elements in the physical twin network corresponding to AMF, to build a verification environment.

[0114] In one possible implementation, NDTF-C can also configure verification resources (such as bandwidth resources) for the verification environment. Alternatively, it can configure basic data (such as user data and / or service-related data) for each digital twin functional network element (or physical twin functional network element). The basic data can come from network elements in the actual physical network corresponding to the digital twin functional network element (or physical twin functional network element); or it can be simulated basic data derived by NDTF-C (or NDTF-E) based on the data characteristics of the basic data of the network elements in the corresponding actual physical network.

[0115] Data is offloaded based on network elements required (or dependent on) for service verification, including AMF, NRF, SMF, and UPF. The data offloading strategy can be to offload 90% of service messages (or simulated service messages) to the digital twin network (i.e., the first verification environment built on the data twin network) and 10% to the physical twin network (i.e., the second verification environment built on the physical twin network). NDTF-C can call the digital twin functional network elements corresponding to AMF, NRF, SMF, and UPF in the digital twin network to build the first verification environment; and call the digital twin functional network elements corresponding to AMF, NRF, SMF, and UPF in the physical twin network to build the second verification environment. Both the first and second verification environments are used for service verification.

[0116] Similarly, NDTF-C can also configure verification resources (such as bandwidth resources) for the verification environment (such as the first verification environment or the second verification goggles). Alternatively, it can configure basic data (such as user data and / or service-related data) for each digital twin functional network element (or physical twin functional network element). The basic data can come from the network elements in the actual physical network corresponding to the digital twin functional network element (or physical twin functional network element); or it can be simulated basic data derived by NDTF-C (or NDTF-E) based on the data characteristics of the basic data of the network elements in the corresponding actual physical network.

[0117] Understandably, the aforementioned function offloading or data offloading strategies can be determined autonomously by NDTF-C. For example, when using function offloading, NDTF-C can determine, based on the multiple network elements upon which service verification depends, which network elements (or their functions) will be executed in the digital twin network, and which will be executed in the physical twin network. Similarly, when using data offloading, NDTF-C can determine the proportion of service messages (or simulated service messages) offloaded to the digital twin network and the physical twin network.

[0118] Of course, the aforementioned function offloading strategy or data offloading strategy can also be determined by NDTF-C based on the service verification request. For example, the service verification request may include second information indicating at least one physical twin functional network element for function offloading in the physical twin network and / or at least one data twin functional network element for function offloading in the digital twin network. NDTF-C can determine the function offloading strategy based on the multiple functional network elements on which the network service depends, as well as the second information, and then configure the verification environment.

[0119] As an example: the network elements that the network services depend on include AMF, NRF, SMF, and UPF. The second information indicates that the at least one physical twin functional network element for function offloading in the physical twin network is the physical twin functional network element corresponding to AMF. The function strategy determined by NDTF-C is that the offloading strategy is to place the functions of network elements such as NRF, SMF, and UPF in the digital twin network, and place the functions of AMF in the physical twin network.

[0120] In one possible implementation, for data offloading, NDTF-C can also build a first verification environment based on a digital twin network by using a verification sandbox built with a digital twin model.

[0121] Understandably, a network service requires multiple network elements, and these elements may involve various protocols. Therefore, data twin technology is needed to model different network elements and protocols. This model may include many types of models, such as network topology models, network structure models, performance models, connection models, behavior models, resource models, call models, network element mechanism models, scheduling models, traffic models, and functional scenario models. Each different model is used to represent the digital simulation of a part of the network element or behavior. A service needs to integrate multiple models to form a fused scenario-based model, or to combine multiple models in series according to the business process requirements to form a model inter-call relationship for model fusion. The process of building a twin verification sandbox in NDTF-C is the process of digital simulation using different twin models. For example, to simulate Pod containers, a resource model related to the telecom cloud can be used; to simulate different NFs (i.e., network elements), a network mechanism model of different NFs can be used; to simulate changes in business traffic, a business traffic model can be used; and to simulate a certain business processing, a fusion of network element behavior models and functional models can be used, etc.

[0122] Therefore, in one possible implementation, NDTF-C can also determine the models required by network services based on the network elements on which the network services depend, and then fuse the required models (e.g., by concatenating and combining the required models according to the business process requirements) to obtain a fused model. Basic data (such as user data and / or business-related data) is then configured for the fused model, thereby obtaining the first verification environment (also known as a verification sandbox) built on the digital twin network.

[0123] S603: NDTF-C obtains the verification results of network services. The verification results are determined by verifying the service capabilities of the network services in the verification environment.

[0124] After configuring the verification environment, the service capabilities of network services can be verified within it to obtain verification results for the target network service. Verification of network service capabilities can include verifying various service metrics. For example, if the service requirements for a session are a session initiation success rate of no less than 99.99% and a session establishment latency of no more than 100ms, the session initiation success rate and latency can be verified to obtain verification results for each service metric. Furthermore, based on the verification results of each service metric, it can be determined whether each service metric meets the service requirements, and so on.

[0125] For business messages used for business verification (such as session establishment requests for terminal devices for session service services), they can be obtained from the actual physical network by NDTF-C (or NDTF-E), for example, from the actual core network.

[0126] In one possible implementation, considering the potential security risks associated with transmitting real business messages (also known as raw data) across domains (such as between a real physical network and a data twin network), and since business verification often relies on the characteristic representation of the actual business messages, in this embodiment, the NDTF-C (or NDTF-E) can subscribe to data features from the physical network and / or the physical twin network (i.e., the NFs in the physical network and / or the physical twin network), obtain the data features of the business messages corresponding to the network services from the physical network and / or the physical twin network, and generate simulated business messages based on the data features of the business messages for business verification.

[0127] Data characteristics can include information such as data attributes, data changes, data composition, data type, and data generation frequency. The following is an example of possible data characteristics generated by a PCF network element, including: Data type: such as policy data; Data attributes: such as UE route selection policy (URSP), slice selection, session and service continuity (SSC) mode, DNN, and access type; Data changes: such as policy changes caused by changes in subscribed data, and linked updates to subscribed data; Data frequency: such as changes occurring every 5 minutes (min); Data composition: such as changing the slice SSC mode while keeping other aspects unchanged; Data size: such as a data message packet size of 8.6K; Data protocol: such as Hypertext Transfer Protocol (HTTP)2; Data packetization: such as packetizing data into 2K packets if necessary. Based on the data characteristics of the service message, NDTF-C or NDTF-E can generate simulated service messages.

[0128] For business verification, a data splitting approach is adopted. In one possible implementation, NDTF-C or NDTF-E can split simulated business messages to a first verification environment built on a digital twin network and a second verification environment built on a physical twin network, according to the data splitting strategy.

[0129] In another possible implementation, the NDTF-C can send a data diversion strategy to the service distribution function network element (such as SDF). After the NDTF-C or NDTF-E determines the simulated service message, it can send the simulated service message to the service distribution function network element. The service distribution function network element will then divert the simulated service message to the first verification environment built on the digital twin network and the second verification environment built on the physical twin network according to the data diversion strategy.

[0130] For data offloading, a function offloading approach is adopted. NDTF-C can provide function offloading strategies to NDTF-E. When NDTF-E builds a verification environment (such as a sandbox environment), the functional network elements in the digital twin network and the physical twin network are connected in a task-driven manner.

[0131] In one possible implementation, for data decentralization, after the second verification environment built on the physical twin network performs business verification, if feature data corresponding to new business messages is generated, the feature data can be fed back to NDTF-C or NDTF-E. NDTF-C or NDTF-E will then generate simulated business messages based on the new feature data and perform simulation iterations on the simulated business messages.

[0132] Understandably, the service capabilities of network services can be iteratively verified in multiple rounds based on the verification environment. For each round of iterative verification, NDTF-C can also evaluate the process and results of the current round of iterative verification.

[0133] The digital twin network (or the first verification environment built based on the digital twin network) and the physical twin network (or the second verification environment built based on the physical twin network) are executed separately, each generating its own simulation results. The physical twin network produces results from the actual operation of network elements, and its results are consistent with the actual network element operation process in the physical network; therefore, the results can be considered as true reference results. The digital twin network produces simulation results through network element simulation and model abstraction, and its results may theoretically have some deviations. NDTF-C can compare the results of physical twin network verification runs with those of digital twin network verification runs in real time or periodically to assess the magnitude of the deviation in the current digital twin network and perform corresponding analysis based on the deviation. Possible causes of this deviation include: characteristic discrepancies between the simulated and actual results of the digital twin network; discrepancies between the proportion of intermediate messages in the simulated process and the proportion of actual messages generated by real network elements (i.e., different process characteristics); discrepancies between the simulated basic user data and the original user data of the network elements (i.e., different data foundations); and errors in the twin model's abstraction of actual network elements and behaviors. This process deviation stems from the twin system's own capabilities and represents a deviation from the actual operating results. When the deviation is significant, self-optimization is generally required, including optimizing the corresponding message data and the twin model, to reduce this simulation deviation. This is rarely mentioned in existing twin solutions, and such a correction method is lacking.

[0134] Therefore, for data offloading, NDTF-C can acquire the first operational data corresponding to the first verification environment and the second operational data corresponding to the second verification environment; based on the first and second operational data, it can determine the deviation of the first verification environment relative to the second verification environment; and adjust the first verification environment according to the deviation. For example, it can adjust the twin models and / or basic data corresponding to each data twin functional network element in the first verification environment (such as a sandbox environment) according to the deviation.

[0135] As an example, NDTF-C can compare first-run data (such as intermediate data generated by a data twin functional network element, or result data generated by business operations) with second-run data (such as intermediate data generated by a physical twin functional network element, or result data generated by business operations). Data comparison can be achieved through various methods, including feature comparison, attribute comparison, and magnitude comparison, which this application does not limit. If discrepancies exist, the twin model of the data twin functional network element in the first verification environment can be adjusted based on these discrepancies. For example, if the value of the intermediate data generated by the data twin functional network element is higher than the value of the intermediate data generated by the physical twin functional network element, the parameters in the twin model corresponding to the data twin functional network element can be adjusted to lower the value of the intermediate data generated by the data twin functional network element. Conversely, if the value of the intermediate data generated by the data twin functional network element is lower than the value of the intermediate data generated by the physical twin functional network element, the parameters in the twin model corresponding to the data twin functional network element can be adjusted to increase the value of the intermediate data generated by the data twin functional network element, and so on. It is understood that the value of the intermediate data here can be a vector or matrix used to represent the intermediate data.

[0136] In addition, if deviations exist, the data can be optimized. Data optimization can be based on basic data. Generally, there is some pre-set user data in the telecommunications business domain, that is, simulated user data information. When the simulated user data information is incorrect, some unexpected or abnormal results may occur. Even through a physical twin network, errors will occur when running in actual network elements. This indicates that it is not necessarily a model error, but a problem with the basic data. It is necessary to regenerate the basic data (for example, to obtain the basic data again from the actual physical network, or to obtain the data characteristics of the basic data from the actual physical network and derive simulated basic data) and re-verify it, which is to optimize the basic data.

[0137] In one possible implementation, NDTF-C can also verify whether the service capabilities of network services meet the service requirements. If they do not meet the service requirements, it can analyze the reasons for the failure or adjust the service itself to conduct subsequent iterative service verification.

[0138] In addition, NDTF-C can also generate business verification reports, such as summarizing and analyzing the verification results corresponding to multiple iterations of verification, generating verification result reports, and feeding them back to the verification requester.

[0139] The following section uses an NDTF architecture that separates NDTF-C and NDTF-E, and combines them respectively. Figure 7 and Figure 8 For the example above Figure 6 The embodiments are described below.

[0140] Figure 7 This application provides a schematic diagram of a business verification process, which includes:

[0141] S701: NDTF-C and NDTF-E send registration requests to the NRF, and correspondingly, NDTF-C and NDTF-E receive registration requests. The NDTF-C or NDTF-E identifier may be carried in the registration request sent to the NRF by NDTF-C or NDTF-E.

[0142] For example, after deployment, NDTF-C and NDTF-E can send registration requests to the NRF to register. After registration, other network elements (NFs) can discover NDTF-C and NDTF-E through the NRF and send messages or data to them, such as sending service verification requests to NDTF-C. Simultaneously, NDTF-E can also subscribe to the status and attributes of other network elements (NFs) to obtain the status data and model data of the corresponding verification network elements during the service verification process.

[0143] S702: The authentication requester sends a service authentication request to the NDTF-C, and the NDTF-C receives the service authentication request accordingly. The service authentication request includes the service requirements of the network service.

[0144] S703: Based on the service verification request, configure the verification environment corresponding to the network service based on the digital twin network and physical twin network corresponding to the physical network.

[0145] Taking data offloading for service verification as an example, after receiving a service verification request, NDTF-C can analyze and determine the network elements on which the network service depends, and determine the models required by the network service, such as the twin models corresponding to each network element. It can then fuse the required models (e.g., by concatenating and combining the required models according to the service process) to obtain a fused model. In addition, NDTF-C can also obtain basic data (such as user data) from each network element, or obtain signaling feature description information (such as data features) corresponding to the basic data of each network element. The signaling feature description information can be used to derive simulated basic data.

[0146] NDTF-C can send the fusion model and the basic data of each network element or the signaling feature description information corresponding to the basic data to NDTF-E. NDTF-E then constructs the first verification environment (also known as the verification sandbox) based on the fusion model and the basic data or simulated basic data of each network element.

[0147] NDTF-C can also call the corresponding physical twin functional network elements in the physical twin network to form a second verification environment based on the network elements on which the service verification depends. Of course, the physical twin network can also be used directly as the second verification environment.

[0148] NDTF-E can subscribe to data features from physical networks and / or physical twin networks (i.e., NFs in physical networks and / or physical twin networks), obtain data features of service messages corresponding to network services from physical networks and / or physical twin networks, and generate simulated service messages based on the data features of service messages.

[0149] S704: Verify the service capabilities of network services through a verification environment.

[0150] As an example, NDTF-C can send data offloading policies to NDTF-E, such as offloading 99% of service messages to the first verification environment built on a digital twin network and offloading 1% of service messages to the second verification environment built on a physical twin network.

[0151] S705: NDTF-C sends the verification result to the verification requester, and the verification requester receives the verification result accordingly.

[0152] The verification results can include information on various business indicators of network services, as well as information on whether each business indicator meets business requirements, etc.

[0153] In one possible implementation, NDTF-C can also acquire first running data corresponding to the first verification environment and second running data corresponding to the second verification environment; determine the deviation of the first verification environment relative to the second verification environment based on the first running data and the second running data; and adjust the first verification environment based on the deviation (e.g., adjust the model / configuration (e.g., basic data configuration) corresponding to the first verification environment).

[0154] In addition, NDTF-C can also perform verification result analysis. For example, if the service performance does not meet the service requirements, it can also analyze the reasons for the failure (such as insufficient configuration of verification resources (such as bandwidth) or excessively high service requirements) and provide feedback to the verification requester for subsequent iterative service verification.

[0155] NDTF-C can also generate business verification reports, such as summarizing and analyzing the verification results of multiple iterations, generating verification result reports, and providing feedback to the verification requester. After completing all verifications, NDTF-C can also instruct NDTF-E to release the temporary verification sandbox (such as the first verification environment).

[0156] The above Figure 7 The service verification process can be mainly applied to core network service verification. There are no specific limitations on this type of network service. It can be an enhancement service based on the current network capabilities or a new functional extension of the current network capabilities. There can also be various forms of services. Generally, the form of this service depends on the operator's network operation needs. The service verification request can be issued in real time or non-real time.

[0157] Another typical application scenario of this application is the verification of intelligent decisions within a network. These intelligent decisions may originate from intelligent network elements in a 5GC network, intelligent surfaces in a 6GC network, or decisions generated by the intrinsic intelligence of network elements. The source of these decisions can be uniformly considered as the network autonomous engine. Such decision verification is mostly real-time, aiming to evaluate the results of intelligent decisions, provide a deterministic explanation, and reduce the risk of unreliable intelligent decisions. The verification process can be as follows: Figure 8 As shown, with Figure 7 The verification process shown is different in that it verifies the differences in origin and is more inclined to real-time verification; at the same time, its verification process may have multiple parallel verification task sandboxes (such as multiple first verification environments based on digital twin networks), and its verification process is multi-task performed simultaneously.

[0158] The verification results are fed back to the intelligent request source (such as NWDAF). The intelligent request source can perform model tuning or configuration optimization and updates, and its verification environment can be reused to continuously perform repeated verifications in real time. Figure 8 In this context, SLA stands for Service Level Agreement. In network scenarios, SLA monitoring services verify requests.

[0159] Figure 9This is a schematic diagram of the virtual-real integrated network twin verification logic architecture provided in this application embodiment. In this application embodiment, the service verification process can be summarized as follows: After the development of a new network service application is completed, or an intelligent network element or other network element in the network issues a service verification request (also known as a twin verification request), the service verification request can find the corresponding twin function body (such as NDTF) for request processing based on the registered twin capabilities. The twin function body parses the verification request, forms a twin task, decomposes the twin dependency according to the verification scenario, obtains the corresponding resources, and forms a scenario-based twin verification isolation sandbox. The twin functional entity generates virtual verification user data and service data based on the actual physical network's operational network data characteristics, loads them into the corresponding verification sandbox, and generates new network service simulation messages (also known as simulated service messages) through real-time simulation. These new network service simulation messages are then split between the physical twin network and the digital twin network according to scenario strategies via a network data splitter, simultaneously executing virtual and physical verification. After execution in the physical twin environment, new data characteristics are generated. The twin functional entity optimizes the sandbox data and service simulation based on these new data characteristics, iterating until the expected verification result is achieved or the process exits if the result is not met. The process can be evaluated by comparing the verification results of the digital twin and the physical twin, thereby optimizing the verification process, service messages, and verification model. Finally, upon completion of verification, the twin functional entity generates a verification result report and releases the corresponding verification resources.

[0160] In the service verification method provided in this application, end-to-end network new service verification utilizes a fusion of digital twins and physical twins, performing iterative verification based on different data and function traffic splitting. The traffic splitting strategy can be differentiated according to different verification requirements to meet the verification objectives of different types of services. The entire verification process is isolated from the actual physical network, without causing any modifications to the actual physical network, thus ensuring high reliability.

[0161] The verification method can simultaneously satisfy real-time verification requests and non-real-time verification requests, such as verification requests from outside the network and verification requests from inside the network. This verification request invocation method has high flexibility.

[0162] Digital twin functional entities are separated into C and E, where C stands for control and E stands for execution. Twin control and twin execution are separate. In addition to the twin network's policies and control scheduling, twin control (such as NDTF-C) can also control the use of physical twins according to the needs of the twin scenario. Twin execution (such as NDTF-E) is the entity that performs virtual verification execution and is responsible for twin control and task execution.

[0163] The verification process is based on simulated data generated by digital twins. The construction of simulated data and simulated messages depends on actual physical network data and the data characteristics generated after the physical twin is actually running. Furthermore, the simulated data can be continuously improved and optimized through the verification iteration process. Through multiple iterations and simulations, this simulated data and simulated messages can achieve a very high degree of similarity to reality, thus achieving accurate simulation results.

[0164] The digital twin control function compares the results of digital twin simulation with those of physical twin simulation to evaluate the process effect of digital twin simulation in real time, and then generates optimization strategies for digital twin simulation. These strategies are not specifically limited and can include optimizing the twin model, optimizing the twin simulation data, optimizing the twin message format, optimizing the running ratio of different types of messages and data, etc.

[0165] The communication device provided in the embodiments of this application will be described below. Please refer to... Figure 10 , Figure 10 This is a schematic diagram of a communication device according to an embodiment of this application. The communication device may include units or modules corresponding to all or part of the steps in the above method embodiments, and can be used to execute the steps executed by NDTF (or NDTF-C) in the above embodiments. Please refer to the relevant descriptions in the above method embodiments for details.

[0166] like Figure 10 As shown, the communication device 1000 includes a processing unit 1010 and an interface unit 1020, wherein the processing unit 1010 may be a processor or a processing circuit, and the interface unit 1020 may be a transceiver unit or an input / output interface. The communication device 1000 can be used to implement the steps of NDTF (or NDTF-C) execution in the above embodiments.

[0167] When the communication device 1000 is used to implement the steps executed by NDTF (or NDTF-C) in the above embodiments:

[0168] Interface unit 1020 is used to obtain a service verification request, which includes the service requirements of the network service.

[0169] The processing unit 1010 is configured to configure a verification environment corresponding to a network service based on the digital twin network and the physical twin network corresponding to the physical network, according to a service verification request; wherein the verification environment includes a first verification environment built on the digital twin network and a second verification environment built on the physical twin network; or, the verification environment is built based on at least one digital twin functional network element in the digital twin network and at least one physical twin functional network element in the physical twin network; and to obtain the verification result of the network service, wherein the verification result is determined by verifying the service capabilities of the network service in the verification environment.

[0170] In one possible design, the service verification request includes first information, which instructs the service verification to perform function offloading or data offloading; wherein, if the first information instructs the service verification to perform function offloading, the verification environment is constructed based on at least one digital twin functional network element in the digital twin network and at least one physical twin functional network element in the physical twin network; if the first information instructs the service verification to perform data offloading, the verification environment includes a first verification environment constructed based on the digital twin network and a second verification environment constructed based on the physical twin network.

[0171] In one possible design, the first information indicates that the service verification performs functional offloading, and the service verification request also includes second information, which indicates at least one physical twin functional network element that performs functional offloading in the physical twin network; when the processing unit 1010 configures the verification environment corresponding to the network service in the digital twin network and the physical twin network according to the service verification request, it is specifically used to determine multiple network elements that the network service depends on according to the service verification request; and configure the verification environment according to the multiple network elements that the network service depends on and the second information.

[0172] In one possible design, the interface unit 1020 is further configured to obtain data features of service messages corresponding to network services from the physical network and / or physical twin network; the processing unit 1010 is further configured to generate simulated service messages based on the data features; wherein, verifying the service capabilities of network services in the verification environment includes: verifying the service capabilities of network services in the verification environment by simulating service messages.

[0173] In one possible design, the verification environment includes a first verification environment built on a digital twin network and a second verification environment built on a physical twin network. The processing unit 1010 is further configured to determine the data diversion strategy for simulated business messages in the first and second verification environments. The interface unit 1020 is further configured to divert simulated business messages to the first and second verification environments according to the data diversion strategy.

[0174] In one possible design, when the interface unit 1020 distributes the simulated service message to the first verification environment and the second verification environment according to the data distribution strategy, it is specifically used to send the data distribution strategy to the service distribution function network element. The data distribution strategy is used by the service distribution function network element to distribute the simulated service message to the first verification environment and the second verification environment.

[0175] In one possible design, the interface unit 1020 is further configured to acquire first running data corresponding to the first verification environment and second running data corresponding to the second verification environment; the processing unit 1010 is further configured to determine the deviation of the first verification environment relative to the second verification environment based on the first running data and the second running data; and adjust the first verification environment based on the deviation.

[0176] In one possible design, the business requirements include at least one business indicator of the network service. When the processing unit 1010 obtains the verification result of the network service, it is specifically used to obtain the verification result of at least one business indicator; and to determine the verification result of the network service based on the verification result of at least one business indicator.

[0177] like Figure 11 As shown, this application also provides a communication device 1100, including a processor 1110 and a communication interface 1120. The processor 1110 and the communication interface 1120 are coupled to each other. It is understood that the communication interface 1120 can be a transceiver, an input / output interface, an input interface, an output interface, an interface circuit, etc. Optionally, the communication device 1100 may also include a memory 1130 for storing instructions executed by the processor 1110, or storing input data required by the processor 1110 to execute instructions, or storing data generated after the processor 1110 executes instructions. The memory 1130 can be a physically independent unit, or it can be coupled to the processor 1110, or the processor 1110 may include the memory 1130.

[0178] When the communication device 1100 is used to implement the steps executed by NDTF (or NDTF-C) in the above embodiments, the processor 1110 can be used to implement the function of the processing unit 1010, and the communication interface 1120 can be used to implement the function of the interface unit 1020.

[0179] In this application embodiment, the processor (e.g., processor 1110) can be one or more central processing units (CPUs). If the processor is a CPU, it can be a single-core CPU or a multi-core CPU. The processor can also be one or a combination of several of the following: CPU, general-purpose processor, application-specific integrated circuit (ASIC), digital signal processor (DSP), microprocessor unit (MPU), microcontroller unit (MCU), graphics processing unit (GPU), field-programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, artificial intelligence processor (AI processor), or neural processing unit (NPU). The processor can implement or execute the methods, steps, and logic block diagrams disclosed in this application embodiment. The steps of the methods disclosed in this application embodiment can be directly manifested as being executed by a hardware processor, or executed by a combination of hardware and software modules within the processor.

[0180] In this embodiment, the memory (e.g., memory 1130) may include, but is not limited to, cache, read-only memory (ROM), random access memory (RAM), synchronous dynamic random access memory (SDRAM), hard disk drive (HDD) or solid-state drive (SSD), erasable programmable read-only memory (EPROM), or compact disc read-only memory (CD-ROM), etc. Memory is any other medium capable of carrying or storing desired program code having an instruction or data structure form and accessible by a computer, but is not limited thereto. The memory in this embodiment may also be a circuit or any other device capable of implementing storage functions for storing computer programs or instructions, and / or data.

[0181] It is understood that the method steps in the embodiments of this application can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, registers, hard disks, portable hard disks, CD-ROMs, or any other form of storage medium well known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. Additionally, the ASIC can reside in a network device or a terminal device. Alternatively, the processor and storage medium can exist as discrete components in the network device or terminal device.

[0182] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this application are performed entirely or partially. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user equipment, or other programmable device. The computer program or instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program or instructions can be transferred from one network device, terminal, computer, server, or data center to another network device, terminal, computer, server, or data center via wired or wireless means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; it can also be an optical medium, such as a digital video optical disc; or it can be a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or non-volatile storage medium, or may include both types of storage media.

[0183] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0184] Additionally, it should be understood that in the embodiments of this application, the term "exemplary" is used to indicate that it is an example, illustration, or description. Any embodiment or design scheme described as "exemplary" in this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the term "exemplary" is intended to present the concept in a concrete manner.

[0185] It is understood that the various numerical designations used in the embodiments of this application are merely for descriptive convenience and are not intended to limit the scope of the embodiments of this application. The order of the process numbers described above does not imply the order of execution; the execution order of each process should be determined by its function and internal logic.

Claims

1. A business verification method, characterized in that, include: Obtain a service verification request, wherein the service verification request includes the service requirements of the network service; Based on the service verification request, configure the verification environment corresponding to the network service based on the digital twin network and physical twin network corresponding to the physical network; Obtain the verification result of the network service, which is determined by verifying the service capabilities of the network service in the verification environment; The verification environment includes a first verification environment built on the digital twin network and a second verification environment built on the physical twin network; or, the verification environment is built on at least one digital twin functional network element in the digital twin network and at least one physical twin functional network element in the physical twin network.

2. The method as described in claim 1, characterized in that, The service verification request includes first information, which instructs the service verification to perform function-based traffic splitting or data-based traffic splitting; wherein... If the first information indicates that service verification is performed by function offloading, the verification environment is constructed based on at least one digital twin functional network element in the digital twin network and at least one physical twin functional network element in the physical twin network; If the first information indicates that the service verification performs data diversion, the verification environment includes a first verification environment built on the digital twin network and a second verification environment built on the physical twin network.

3. The method as described in claim 1 or 2, characterized in that, The first information indicates that the service verification performs function offloading, and the service verification request further includes second information, which indicates the at least one physical twin function network element that performs function offloading in the physical twin network; Based on the service verification request, configure the verification environment corresponding to the network service in the digital twin network and the physical twin network, including: Based on the service verification request, determine the multiple network elements on which the network service depends; Configure the verification environment based on the multiple network elements on which the network service depends and the second information.

4. The method according to any one of claims 1-3, characterized in that, The method further includes: Obtain the data characteristics of the service messages corresponding to the network services from the physical network and / or the physical twin network; Based on the data characteristics, generate simulated business messages; The verification of the service capabilities of the network service in the verification environment includes: The network service capabilities are verified in the verification environment using the simulated service messages.

5. The method as described in claim 4, characterized in that, The verification environment includes a first verification environment built based on the digital twin network and a second verification environment built based on the physical twin network. The method further includes: Determine the data splitting strategy for simulated business messages in the first verification environment and the second verification environment; According to the data diversion strategy, the simulated business messages are diverted to the first verification environment and the second verification environment.

6. The method as described in claim 5, characterized in that, The step of diverting the simulated business messages to the first verification environment and the second verification environment according to the data diversion strategy includes: The data diversion strategy is sent to the service distribution function network element, and the data diversion strategy is used by the service distribution function network element to divert the simulated service message to the first verification environment and the second verification environment.

7. The method as described in claim 5 or 6, characterized in that, The method further includes: Obtain the first running data corresponding to the first verification environment and the second running data corresponding to the second verification environment; Based on the first running data and the second running data, determine the deviation of the first verification environment relative to the second verification environment; Adjust the first verification environment based on the deviation.

8. The method according to any one of claims 1-7, characterized in that, The business requirements include at least one business indicator of the network service, and obtaining the verification result of the network service includes: Obtain the verification result of at least one of the business metrics; The verification result of the network service is determined based on the verification result of at least one of the business indicators.

9. A communication device, characterized in that, Includes modules or units for performing the method as described in any one of claims 1-8.

10. A communication device, characterized in that, It includes a processor and an interface circuit, the interface circuit being used for inputting and / or outputting signals, and the processor being used to implement the method as described in any one of claims 1-8 through logic circuits or executing instructions.

11. The apparatus as claimed in claim 10, characterized in that, It also includes a memory for storing the instructions.

12. A computer program product, characterized in that, It includes a computer program or instructions that, when executed by a processor, cause the method as described in any one of claims 1-8 to be implemented.

13. A computer-readable storage medium, characterized in that, The storage medium stores a computer program or instructions that, when executed by a processor, cause the method as described in any one of claims 1-8 to be implemented.

Images