Twin model construction method and device and computer device

Abstract

The application relates to the technical field of networks, in particular to a twin model construction method and device and computer equipment. The method comprises the following steps: in the case that a digital twin demand for a target service is acquired, constructing a network element slice model according to network element capabilities required for realizing the target service; constructing a network element function model according to network element functions required for possessing the network element capabilities; constructing a network element instruction model according to execution instructions required for possessing the network element functions; assembling the network element slice model, the network element function model and the network element instruction model to obtain a digital twin model; wherein the digital twin model is used for realizing the target service.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of network, in particular to a twin model construction method and device and computer equipment. BACKGROUND

[0002] Network Element: refers to a device with specific functions and independent operation capabilities in a communication network, which is the basic unit of the communication network and is responsible for completing various communication tasks. The network element can be a physical device such as a switch, a router, a base station, etc., or a software entity such as a protocol stack, an application program, etc. Generally speaking, for a communication operator, the network element refers to various communication devices and apparatuses such as Access and Mobility Management Function (AMF), Session Management Function (SMF), User Plane Function (UPF), Network Repository Function (NRF), router, server, etc.

[0003] Network Digital Twin: a new technology concept that creates a virtual copy of a physical network to realize real-time monitoring, analysis and optimization of network status. This not only involves data collection and processing, but also includes network behavior simulation, network performance prediction and potential problem diagnosis. The core of network digital twin is to build a virtual model corresponding to the physical network through data collection, simulation modeling, etc., i.e. digital twin model. This virtual model can reflect the configuration, topology, state and behavior of the physical network, and can be mapped to the physical network in real time.

[0004] In the traditional technology, the modeling method of network element digital twin and network digital twin has large granularity, which cannot accurately model the network element. SUMMARY

[0005] Therefore, it is necessary to provide a twin model construction method, device and computer equipment capable of improving the modeling accuracy of digital twin model to solve the above technical problems.

[0006] In a first aspect, the present application provides a twin model construction method, which comprises:

[0007] After obtaining the digital twin demand for the target service, a network element slicing model is constructed according to the network element capability required to realize the target service.

[0008] constructing a network element function model according to network element functions required by the network element capability;

[0009] constructing a network element instruction model according to execution instructions required by the network element function;

[0010] assembling the network element slice model, the network element function model and the network element instruction model to obtain a digital twin model; wherein the digital twin model is used to implement a target service.

[0011] In one of the embodiments, the network element slice model is constructed according to a network element capability required by the target service, including:

[0012] determining a target network element type required by the network element capability according to the network element capability required by the target service;

[0013] constructing the network element slice model in a slice model construction manner corresponding to the target network element type.

[0014] In one of the embodiments, the network element capability includes at least two independent sub-capabilities, and each sub-capability corresponds to a target network element type.

[0015] In one of the embodiments, the network element function model is constructed according to network element functions required by the network element capability, including:

[0016] for each sub-capability, constructing a corresponding network element function model according to network element functions required by the sub-capability.

[0017] In one of the embodiments, the network element function includes at least one hardware configuration function and at least one network configuration function; different hardware configuration functions are independent of each other, and different network configuration functions are independent of each other.

[0018] In one of the embodiments, the method further includes: according to the network element function, querying execution instructions required by the network element function in an instruction library.

[0019] In one of the embodiments, the method further includes: according to the network element function, querying execution instructions required by the network element function in an instruction library; wherein the instruction library stores instruction sets corresponding to different providers, and the instruction set is determined according to an instruction document.

[0020] In one of the embodiments, the network element slice model, the network element function model and the network element instruction model are assembled to obtain a digital twin model, including:

[0021] respectively verifying the integrity of the network element slice model, the network element function model and the network element instruction model;

[0022] According to the service requirement of the target service, a model action is added to the network element slice model, the network element function model and the network element instruction model which pass the integrity verification;

[0023] The network element slice model, the network element function model and the network element instruction model to which the model action is added are assembled to obtain a digital twin model.

[0024] In one of the embodiments, the network element slice model, the network element function model and the network element instruction model to which the model action is added are assembled to obtain the digital twin model, including:

[0025] The network element instruction model to which the model action is added is associated with the network element function model to which the model action is added to obtain an associated network element function model;

[0026] The associated network element function model is associated with the network element slice model to which the model action is added;

[0027] The associated network element slice model is taken as the digital twin model.

[0028] In a second aspect, the present application further provides a twin model construction device, including:

[0029] A slice construction module is configured to, in a case where a digital twin requirement for a target service is acquired, construct a network element slice model according to a network element capability required for implementing the target service;

[0030] A function construction module is configured to construct a network element function model according to a network element function required for possessing the network element capability;

[0031] An instruction construction module is configured to construct a network element instruction model according to an execution instruction required for possessing the network element function;

[0032] A twin model construction module is configured to assemble the network element slice model, the network element function model and the network element instruction model to obtain a digital twin model; wherein the digital twin model is used for implementing the target service.

[0033] In a third aspect, the present application further provides a computer device including a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0034] In a case where a digital twin requirement for a target service is acquired, a network element slice model is constructed according to a network element capability required for implementing the target service;

[0035] A network element function model is constructed according to a network element function required for possessing the network element capability;

[0036] A network element instruction model is constructed according to an execution instruction required for possessing the network element function;

[0037] The network element slice model, the network element function model and the network element instruction model are assembled to obtain a digital twin model; wherein the digital twin model is used to realize the target service.

[0038] In a fourth aspect, the present application also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the following steps:

[0039] In a case where the digital twin requirement for the target service is acquired, a network element slice model is constructed according to a network element capability required for realizing the target service;

[0040] A network element function model is constructed according to a network element function required for possessing the network element capability;

[0041] A network element instruction model is constructed according to an execution instruction required for possessing the network element function;

[0042] The network element slice model, the network element function model and the network element instruction model are assembled to obtain a digital twin model; wherein the digital twin model is used to realize the target service.

[0043] In a fifth aspect, the present application also provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the following steps:

[0044] In a case where the digital twin requirement for the target service is acquired, a network element slice model is constructed according to a network element capability required for realizing the target service;

[0045] A network element function model is constructed according to a network element function required for possessing the network element capability;

[0046] A network element instruction model is constructed according to an execution instruction required for possessing the network element function;

[0047] The network element slice model, the network element function model and the network element instruction model are assembled to obtain a digital twin model; wherein the digital twin model is used to realize the target service.

[0048] The instruction-level modeling in the application can capture the bottom-layer characteristics and behaviors of the network element device in detail, and provide a solid foundation for subsequent function-level and network element-level modeling. The function-level modeling can abstract the middle-layer characteristics of the network element device, so that the model is more reusable and extensible. Meanwhile, through the function-level modeling, the network element device can be more easily verified in function and optimized in performance. The network element-level modeling can comprehensively reflect the actual running situation and business demand of the network element device, and provide the final output for the construction of the digital twin model. Meanwhile, through the network element-level modeling, the full life cycle management and optimization of the network element device can be realized. Compared with the traditional technology, the application performs hierarchical modeling from the instruction level to the function level and then to the network element level, which not only can capture the network element characteristics at different levels in detail, but also ensures the integrity and correctness of the model, and improves the flexibility and adaptability of the model. BRIEF DESCRIPTION OF DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the application or the related art, the following will briefly introduce the drawings needed to be used in the description of the embodiments of the application or the related art. Obviously, the drawings in the following description only some embodiments of the application, and for those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0050] Figure 1 A flowchart of a method for constructing a twin model in an embodiment;

[0051] Figure 2 A schematic diagram of the hierarchical relationship among the network element slice model, the network element function model and the network element instruction model in an embodiment;

[0052] Figure 3 A flowchart of a step of obtaining a digital twin model in an embodiment;

[0053] Figure 4 A flowchart of a step of assembling the network element slice model, the network element function model and the network element instruction model of the adding model action type in an embodiment;

[0054] Figure 5 A flowchart of a step of constructing a network element slice model in an embodiment;

[0055] Figure 6 A block diagram of a structure of a twin model construction device in an embodiment;

[0056] Figure 7 An internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0057] In order to make the purposes, technical solutions and advantages of the present application clearer, further detailed description will be given below in combination with the drawings and examples. It should be understood that the specific examples described herein are only used to explain the present application and not to limit the present application.

[0058] In one exemplary embodiment, as shown in Figure 1 a twin model construction method is provided. Taking the case of applying the method to a computer device, the method includes the following S101 to S104. Among them:

[0059] S101, in the case of obtaining the digital twin demand for the target service, according to the network element capability required to realize the target service, a network element slicing model is constructed.

[0060] It can be understood that network elements play a crucial role in communication networks, they are the basic units to realize specific communication functions, and the target service realized by network elements refers to how these network elements support and promote the operation of various communication services. The network element capability required to realize the target service mainly refers to the functions and characteristics possessed by the basic components or devices constituting the communication network, and these network elements can work together to support the operation of the target service.

[0061] For example, taking the data network name (DNN) service as an example, in the 5th generation mobile communication technology (5G) network, DNN is a key concept, which is similar to the access point name (APN) in the 4G era, used to distinguish different data network access, and according to DNN, the session is shunted to different SMF and UPF, so as to realize customer-oriented access. In the DNN service, the role of network elements (i.e. network element capability) mainly reflects in the following aspects:

[0062] (1) Access and shunting capability: base station (BS) as a component of wireless access network, is responsible for wireless communication with user equipment (such as mobile phone), providing coverage and connection. When user equipment initiates a data session request, base station will forward the session request to the corresponding network element in the core network according to the DNN information. The access and mobility management function (AMF) in the core network will select appropriate SMF and UPF according to DNN to realize the shunting and management of session.

[0063] (2) Session management and policy control capability: The session management function (SMF) is responsible for the establishment, modification, and release of sessions, as well as the policy control related to sessions. The SMF will allocate appropriate UPFs for sessions according to the DNN and business requirements, and ensure that the data transmission of the session is in accordance with the predetermined policy. At the same time, the SMF is also responsible for the collection and reporting of charging data of the session.

[0064] (3) User plane data processing capability: The user plane function (UPF) is responsible for data processing and forwarding in the user plane. The UPF will perform necessary processing (such as encryption, decryption, firewall inspection, etc.) on the data packets from the user equipment according to the instructions of the SMF, and forward the data packets to the destination network or application server. In DNN business, the selection and configuration of UPF directly affect the performance and security of data transmission.

[0065] (4) Network slicing support capability: 5G network supports network slicing technology, which can create multiple logically independent virtual networks according to different business requirements. In DNN business, network slicing technology can ensure that data sessions of different customers or businesses are logically isolated, improving the utilization efficiency of network resources and the security of business. Network elements need to support network slicing technology to ensure that DNN business can be deployed and migrated flexibly between different slices according to the predetermined policy.

[0066] Optionally, according to the capabilities required to achieve the target business, constructing a network element slice model means digitizing the business logic, operation process, device state, and other information in the physical world, and reconstructing and simulating them in virtual space to achieve comprehensive monitoring, optimization, and management of physical objects; for example, the above-mentioned (1) access and distribution capability corresponds to network element slice model 1, the above-mentioned (2) session management and policy control corresponds to network element slice model 2, the above-mentioned (3) user plane data processing corresponds to network element slice model 3, and the above-mentioned (4) network slicing support capability corresponds to network element slice model 4.

[0067] S102, according to the network element functions required by the network element capabilities, construct a network element function model.

[0068] It can be understood that each network element capability is realized through network element functions. For example, the network element slice model 2 corresponding to the session management and policy control network element capability includes the following functional units, as shown in Table 1:

[0069] Table 1

[0070]

[0071] Optionally, each functional unit corresponds to a network element function model, which is used to implement the functional unit. For each functional unit, its corresponding network element function model is independent, because different functional units play different roles in the network, have different functions and behaviors. For example, the function model of the base station will describe in detail how to communicate with user equipment, how to process uplink and downlink data, how to allocate resources, etc.; while the function model of the mobile switch or session management function in the core network will describe how to handle user mobility, how to establish and manage sessions, how to perform policy control, etc.

[0072] In this embodiment, the network element function models under the same network element capability are aggregated to obtain a network element slice model. By aggregating these network element function models, a more comprehensive and easier-to-manage network element slice model can be obtained, which can reflect the overall performance and behavior of this network element capability in the network.

[0073] It can be understood that by modularizing the function model, the network can be upgraded and expanded more easily. When new functions need to be added or existing functions need to be optimized, the corresponding network element slice model can be modified or expanded. The network element slice model provides a higher level of abstraction, so that network designers and maintenance personnel can focus more on the overall performance and behavior of the network, rather than on specific implementation details. By aggregating the function model, the utilization of network resources can be better understood and optimized.

[0074] For example, resource allocation can be dynamically adjusted according to the performance indicators of the network element slice model to meet the needs of different business scenarios. The network element slice model makes it easier to maintain and troubleshoot the network. When problems occur, maintenance personnel can quickly locate the relevant network element slice model and perform targeted repair and optimization.

[0075] S103, constructing a network element instruction model according to the execution instructions required for the network element function.

[0076] Each functional unit is implemented by at least one execution instruction, which is the lowest unit of network element capability implementation. For example, as shown in Table 2:

[0077] Table 2

[0078]

[0079] Specifically, after determining any network element capability, the corresponding execution instruction of the network element capability can be obtained from the technical document of the network element manufacturer. The network element capability can involve network communication, data processing, resource management, and other aspects. Then, the official website or related document library of the network element manufacturer is accessed to find the technical document related to the network element capability. These documents can include user manuals, API guides, configuration guides, etc. The documents usually describe the functions, parameters, usage methods, and possible return values of the capability in detail.

[0080] S104, the network element slice model, the network element function model and the network element instruction model are assembled to obtain the digital twin model.

[0081] Specifically, as shown in Figure 2 , for any function unit, the network element instruction model (i.e. instruction model A, instruction model B… instruction model N in Figure 2 ) under the function unit is assembled to the network element function model corresponding to the function unit (for example, slice A function A model, slice A function B model, slice B function B model… slice N function A model in Figure 2 ); for any network element capability, the network element function model under the function unit is assembled to the network element slice model corresponding to the function unit (for example, network element A slice model A, network element A slice model B… network element A slice model N in Figure 2 ).

[0082] In this embodiment, modeling is performed in three levels of granularity, specifically: network element instruction level modeling, network element function model level modeling and network element slice level modeling.

[0083] Among them, the network element instruction model is a complete instruction function of the network element, which can often realize the function of a manufacturer's instruction; the network element function model is an aggregation modeling of a specific function of the network element, which can often realize the function of multiple instructions of the manufacturer's network element; the network element slice model is a modeling of all network element functions required to complete a business, which is often an aggregation of multiple single network element function models.

[0084] In each of the above different levels of models, the capabilities corresponding to each level of model are independent of each other, have no strong dependency relationship, have complete calling methods and input and output parameters, and can independently form atomic capabilities to provide externally. Since the capabilities of different levels are independent of each other, when it is actually necessary to realize a certain network element capability, the existing models can be assembled according to the self-defined requirements to form the corresponding digital twin model. The models of different levels can be opened for reuse and assembled on any network element.

[0085] Then, the network element slice model, the network element function model and the network element instruction model are assembled by level to obtain an initial twin model; and the initial twin model is capability-encapsulated to obtain a digital twin model capable of realizing a target service. The capability-encapsulation of the initial twin model refers to encapsulating specific functions or capabilities in the initially constructed twin model so that these capabilities can provide services or support externally in an independent and reusable form.

[0086] The above-mentioned twin model construction method can capture the bottom-layer characteristics and behaviors of the network element device in detail, and provide a solid foundation for subsequent function-level and network element-level modeling. The function-level modeling can abstract the middle-layer characteristics of the network element device, so that the model is more reusable and extensible. Meanwhile, through the function-level modeling, the network element device can be more easily verified in function and optimized in performance. The network element-level modeling can comprehensively reflect the actual running situation and service demand of the network element device, and provide the final output for the construction of the digital twin model. Meanwhile, through the network element-level modeling, the full life cycle management and optimization of the network element device can be realized. Compared with the traditional technology, the present application performs hierarchical modeling from the instruction level to the function level and then to the network element level, which not only can capture the network element characteristics at different levels in detail, but also ensures the integrity and correctness of the model, and improves the flexibility and adaptability of the model.

[0087] In one exemplary embodiment, in the field of digital twin and modeling, the capability-encapsulation module is a key link for improving modeling efficiency and realizing twin capabilities externally. The module usually includes three sub-modules of action allocation, capability encapsulation and capability assembly, each of which has its specific function and role. As shown in Figure 3 As shown in FIG. 6, the network element slice model, the network element function model and the network element instruction model are assembled to obtain a digital twin model, which includes:

[0088] S301, the network element slice model, the network element function model and the network element instruction model are respectively verified for integrity.

[0089] It can be understood that the network element slice model, the network element function model and the network element instruction model are verified for integrity, which aims to ensure that each model is complete without missing or erroneous parts, thereby laying a solid foundation for the subsequent assembly process.

[0090] Optionally, when the network element slice model, the network element function model and the network element instruction model are respectively verified for integrity, each unit in the model can be tested to ensure that each unit can correctly perform its intended task, and the actual use scenario can also be simulated to test whether the behavior of the model under different conditions meets the expectation.

[0091] S302, according to the service requirement of the target service, adding model actions to the integrity-verified network element slice model, network element function model, and network element instruction model.

[0092] Among them, model actions refer to a series of operations or behaviors performed on models, which are usually closely related to dynamic changes in actual business scenarios. For example, model actions can include:

[0093] 1. Install (Install / Assembly):

[0094] It refers to combining various components or elements in the model according to predetermined methods and rules to form a complete system or structure.

[0095] In digital twin models, install actions can be used to simulate the installation process of equipment, verifying the correctness of the installation steps and the assemblability of the equipment.

[0096] 2. Disassemble (Disassembly):

[0097] In contrast to the install action, the disassemble action refers to separating components or elements in the model.

[0098] In digital twin models, disassemble actions can be used to simulate the disassembly process of equipment, facilitating maintenance, repair, or replacement of parts.

[0099] 3. Modify (Modify / Update):

[0100] It refers to modifying or updating certain parameters, attributes, or structures in the model.

[0101] In digital twin models, modify actions can be used to simulate the upgrade, modification, or optimization process of equipment, verifying the performance and effects after modification.

[0102] 4. Inspect (Inspect / Query):

[0103] It refers to querying, retrieving, or analyzing information in the model.

[0104] In digital twin models, inspect actions can be used to obtain real-time status, historical data, or performance indicators of equipment, supporting decision-making and fault diagnosis.

[0105] 5. Stop (Stop / Deactivate):

[0106] It refers to stopping a certain function, process, or device in the model.

[0107] In digital twin models, stop actions can be used to simulate the shutdown state of equipment, verifying the safety and stability during the shutdown process.

[0108] 6. Resume / Restart:

[0109] In contrast to a stop action, a resume action refers to restoring the normal operation of a function, process, or device in the model.

[0110] In a digital twin model, complex actions can be used to simulate the device restart process and verify the performance and status after restart.

[0111] These model actions play a crucial role in digital twin models, enabling them to more accurately simulate dynamic changes in real-world business scenarios and supporting full lifecycle management, optimization, and decision-making for devices. Furthermore, adding these model actions enhances the interactivity and usability of digital twin models, allowing users to gain a more intuitive understanding of device operating status and performance.

[0112] In this embodiment, business requirements define the specific functions or operations that the model needs to implement, such as device installation, disassembly, modification, querying, stopping, and recovery. These functional requirements are usually closely related to tasks or activities in actual business scenarios. Adding corresponding model actions to different models enables them to possess the corresponding capabilities.

[0113] S303 assembles the network element slice model, network element function model, and network element instruction model with added model actions to obtain a digital twin model.

[0114] The assembly of network element slice models, network element function models, and network element instruction models with added model actions refers to integrating these models according to certain rules and logic. This process may involve matching and connecting the data, interfaces, and logic of each model to ensure they can work together.

[0115] Next, the interaction methods and rules between the models are determined, including data exchange, event triggering, and state updates. These interaction rules ensure that the assembled models form an organic whole, rather than simply being a collection of components. Finally, the assembled digital twin model is verified and tested to ensure that it can correctly simulate real-world business scenarios and meet business requirements. This process may include functional testing, performance testing, and security testing.

[0116] Furthermore, such as Figure 4 As shown, the network element slice model, network element function model, and network element instruction model with added model actions are assembled to obtain a digital twin model, including:

[0117] S401, associate the network element instruction model with the network element function model to which the model action is added, to obtain the associated network element function model.

[0118] Specifically, first determine which instructions or operations in the network element instruction model need to be associated with specific functions or states in the network element function model. Then, establish a mapping relationship between these instructions or operations and the corresponding functions or states in the network element function model. This can be achieved by defining interfaces, data exchange formats or event triggering mechanisms. Finally, test and verify the associated network element function model to ensure that it can correctly respond to instructions from the network element instruction model and perform corresponding functions.

[0119] S402, associate the associated network element function model with the network element slice model to which the model action is added.

[0120] Specifically, first, identify the slices or components in the network element slice model that need to be associated with the function model. Then, map the functions or states in the network element function model to these slices or components to ensure that they can work together. Finally, test the associated network element slice model to verify whether its functions work as expected and whether the interaction with the network element function model is smooth.

[0121] S403, the associated network element slice model as a digital twin model.

[0122] Optionally, after completing the association of the previous two stages, the associated network element slice model obtained is used as a digital twin model. This digital twin model now integrates information from the network element slice, function and instruction three aspects, and can simulate the dynamic changes in the actual business scenario.

[0123] In this embodiment, the function-level twin modeling module not only can be aggregated based on the instruction-level model, but also has the ability to detect and repair missing instruction-level models. This self-healing feature enables the model to automatically adapt to changes in the network environment, supplement missing instructions in a timely manner, and ensure the integrity and effectiveness of the model, thereby improving the robustness and reliability of the entire twin network. Through capability encapsulation and capability assembly, the model can provide services in the form of encapsulated capability packages, which not only simplifies the use process of the model, but also improves the reusability and expandability of the model. Through dynamic allocation of actions and encapsulation assembly, different business requirements can be quickly responded to, and flexible assembly and customization of network element functions can be achieved.

[0124] In an exemplary embodiment, as shown in Figure 5 According to the network element capabilities required to achieve the target business, a network element slice model is constructed, including:

[0125] S501, determining a target network element type required to have network element capabilities according to network element capabilities required to realize a target service.

[0126] Specifically, according to the network element capabilities required to realize the target service, the network element types having these capabilities are identified and determined. This usually involves in-depth analysis of service requirements to determine which network element capabilities (such as data processing, signal transmission, storage functions, etc.) are indispensable to realize the service target. Then, by comparing the existing network element types and their capabilities, the target network element type most suitable for the service requirements is selected.

[0127] S502, constructing a network element slice model using a slice model construction method corresponding to the target network element type.

[0128] Specifically, after determining the target network element type, the next step is to use the slice model construction method corresponding to the type to construct the network element slice model. This usually involves using specific modeling tools, techniques or frameworks to define the structure, behavior and interaction with other network elements or systems of the model according to the characteristics and capabilities of the target network element type.

[0129] Among them, the network element capabilities include at least two independent sub-capabilities, and each sub-capability corresponds to a target network element type.

[0130] Among them, the sub-capabilities are (1) access and distribution capabilities, (2) session management and policy control capabilities, (3) user plane data processing capabilities, and (4) network slice support capabilities.

[0131] Optionally, for each sub-capability, the existing network element type library or expert consultation is searched to find the network element type most matched with the sub-capability. For each target network element type, the network element functions required to realize its sub-capabilities are analyzed, which can specifically include data processing, signal transmission, storage, computing and other functions.

[0132] Correspondingly, according to the network element functions required to have network element capabilities, a network element function model is constructed, including: for each sub-capability, according to the network element functions required to have the sub-capability, a corresponding network element function model is constructed.

[0133] In an exemplary embodiment, the network element functions include at least one hardware configuration function and at least one network configuration function; different hardware configuration functions are independent of each other, and different network configuration functions are independent of each other.

[0134] The hardware configuration function refers to the hardware-related functions in the network element device, such as processor speed, memory capacity, interface type, etc. Different hardware configuration functions are independent of each other, which means that the change of one hardware configuration function will not affect other hardware configuration functions. When building the network element function model, a corresponding model component needs to be created for each hardware configuration function, which should accurately reflect the actual performance and behavior of the hardware.

[0135] The network configuration function refers to the network connection and communication-related functions in the network element device, such as IP address configuration, routing protocol, network security settings, etc. Different network configuration functions are also independent of each other, and the adjustment of one network configuration function will not interfere with the normal operation of other network configuration functions. For network configuration functions, models that can simulate network communication and configuration behavior need to be built, which should be able to handle different network scenarios and configuration options.

[0136] In an exemplary embodiment, the method further comprises: according to the network element function, querying the execution instructions required by the network element function in the instruction library.

[0137] The instruction library stores instruction sets corresponding to different providers, and the instruction sets are determined according to instruction documents.

[0138] It can be understood that the provider is each network element manufacturer, and the instruction library collects instruction sets from multiple network element manufacturers. These instruction sets are indispensable components for building and operating digital twin models. Network element manufacturers are companies or entities that produce and provide network element devices. They develop and maintain corresponding instruction sets according to their own technical specifications and standards. Each network element manufacturer provides a detailed set of instructions, which are usually accompanied by instruction documents. Instruction documents record the content, format and usage of instruction sets in detail.

[0139] In an exemplary embodiment, the embodiment provides a specific embodiment of a digital twin model construction method, comprising:

[0140] S1, constructing a network element slice model according to the network element capabilities required to realize the target service.

[0141] The target service is a DNN service. The network element capabilities required for each type of network element to complete the DNN service are determined by an expert system, and one UDM DNN service opening network element slice model, one SMF DNN service opening network element slice model, and one UPF DNN service opening network element slice model are constructed.

[0142] S2, constructing a network element function model according to the network element functions required to have network element capabilities.

[0143] Among them, under the UDM DNN service opening network element slicing model, the UDM APN OI function model is constructed;

[0144] Among them, under the UPF DNN service opening network element slicing model, the UPF DNN basic configuration function model, the UPF address pool function model, and the UPF terminal mutual visit function model are constructed, and the three models are associated to the UPF DNN service opening network element slicing model.

[0145] Among them, under the SMF DNN service opening network element slicing model, the SMF DNN basic configuration function model and the SMF DNN DNS configuration function model are constructed, and the two models are associated to the SMF DNN service opening network element slicing model.

[0146] S3, according to the execution instruction required by the network element function, a network element instruction model is constructed.

[0147] The SMF new APN DNN instruction level model, the SMF DNN binding 2B default slice instruction level model, the SMF adding DNN and UPF binding relationship instruction level model, the SMF DNN binding bottom-up strategy instruction level model, and the SMF DNN opening PCC function instruction level model are associated to the SMF DNN basic configuration function model.

[0148] S4, the network element slicing model, the network element function model and the network element instruction model are assembled to obtain a digital twin model.

[0149] Specifically, the capabilities of all the network element slicing models are encapsulated to construct a digital twin model of DNN service.

[0150] It should be understood that although each step in the flowchart involved in the above embodiments is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise stated herein, the execution of these steps has no strict sequence limitation, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in the above embodiments can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or steps or stages in other steps.

[0151] Based on the same inventive concept, the embodiments of the present application also provide a twin model construction device for implementing the twin model construction method described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more twin model construction device embodiments provided below can refer to the limitations of the twin model construction method described above, which will not be repeated here.

[0152] In one exemplary embodiment, as shown in Figure 6 a twin model construction device is provided, comprising a slice construction module 11, a function construction module 12, an instruction construction module 13, and a twin model construction module 14, wherein:

[0153] The slice construction module 11 is configured to, in the case of obtaining a digital twin requirement for a target service, construct a network element slice model according to a network element capability required for implementing the target service.

[0154] The function construction module 12 is configured to construct a network element function model according to a network element function required for possessing the network element capability.

[0155] The instruction construction module 13 is configured to construct a network element instruction model according to an execution instruction required for possessing the network element function.

[0156] The twin model construction module 14 is configured to assemble the network element slice model, the network element function model, and the network element instruction model to obtain a digital twin model, wherein the digital twin model is used to implement the target service.

[0157] In one embodiment, the slice construction module 11 is configured to determine a target network element type required for possessing the network element capability according to the network element capability required for implementing the target service.

[0158] The network element slice model is constructed in a slice model construction manner corresponding to the target network element type.

[0159] In one embodiment, the network element capability comprises at least two independent sub-capabilities, and each sub-capability corresponds to a target network element type.

[0160] In one embodiment, the function construction module 12 is configured to, for each sub-capability, construct a corresponding network element function model according to a network element function required for possessing the sub-capability.

[0161] In one embodiment, the network element function comprises at least one hardware configuration function and at least one network configuration function, and different hardware configuration functions are independent of each other and different network configuration functions are independent of each other.

[0162] In one of the embodiments, the apparatus further comprises a querying module, configured to: according to the network element function, query the execution instruction required by the network element function in the instruction library; wherein the instruction library stores the instruction set corresponding to each different provider, and the instruction set is determined according to the instruction document.

[0163] In one of the embodiments, the twin model construction module 14 is configured to: perform integrity verification on the network element slice model, the network element function model and the network element instruction model respectively;

[0164] According to the service requirement of the target service, adding model actions to the network element slice model, the network element function model and the network element instruction model which pass the integrity verification;

[0165] Assembling the network element slice model, the network element function model and the network element instruction model to which the model actions are added to obtain the digital twin model.

[0166] In one of the embodiments, the twin model construction module 14 is configured to: associate the network element instruction model to which the model actions are added to the network element function model to which the model actions are added to obtain the associated network element function model;

[0167] Associating the associated network element function model to the network element slice model to which the model actions are added;

[0168] Taking the associated network element slice model as the digital twin model.

[0169] Each module in the above twin model construction apparatus can be realized by software, hardware and their combination in whole or in part. The above modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to each module.

[0170] In one exemplary embodiment, a computer device is provided, which can be a server, and its internal structure diagram can be as shown in Figure 7As shown in the figure. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through the system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the data of the digital twin model construction method. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with the terminal outside through the network connection. The computer program is executed by the processor to realize a kind of twin model construction method.

[0171] Those skilled in the art can understand that, Figure 7 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0172] In one exemplary embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the following steps:

[0173] In the case where the digital twin demand for the target service is acquired, a network element slicing model is constructed according to the network element capability required to implement the target service;

[0174] A network element function model is constructed according to the network element function required to possess the network element capability;

[0175] A network element instruction model is constructed according to the execution instruction required to possess the network element function;

[0176] The network element slicing model, the network element function model and the network element instruction model are assembled to obtain a digital twin model; wherein the digital twin model is used to implement the target service.

[0177] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the following steps:

[0178] In the case where the digital twin demand for the target service is acquired, a network element slicing model is constructed according to the network element capability required to implement the target service;

[0179] constructing a network element function model according to network element functions required by the network element capability;

[0180] constructing a network element instruction model according to execution instructions required by the network element function;

[0181] assembling the network element slice model, the network element function model and the network element instruction model to obtain a digital twin model; wherein the digital twin model is used to implement the target service.

[0182] In one embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the following steps:

[0183] In the case where the digital twin requirement for the target service is acquired, a network element slice model is constructed according to network element capabilities required by the implementation of the target service;

[0184] constructing a network element function model according to network element functions required by the network element capability;

[0185] constructing a network element instruction model according to execution instructions required by the network element function;

[0186] assembling the network element slice model, the network element function model and the network element instruction model to obtain a digital twin model; wherein the digital twin model is used to implement the target service.

[0187] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0188] The technical features of the above embodiments can be combined in any manner. To make the description concise, not all possible combinations of the technical features in the above embodiments are described, but as long as the combinations of the technical features do not exist contradictions, they should be considered as the scope of the present application.

[0189] The above-described embodiments are merely illustrative of several embodiments of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the scope of the patent. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of protection of the present application should be subject to the appended claims.

Claims

1. A method for constructing a twin model, characterized in that, The method comprises: In the case that the digital twin demand for the target service is acquired, a target network element type required to possess a network element capability required to implement the target service is determined according to the network element capability; the network element capability comprises at least two independent sub-capabilities, and each sub-capability corresponds to a target network element type; A network element slice model is constructed by using a slice model construction mode corresponding to the target network element type; A network element function model is constructed according to a network element function required to possess the network element capability; A network element instruction model is constructed according to an execution instruction required to possess the network element function; The network element slice model, the network element function model and the network element instruction model are assembled to obtain a digital twin model; the digital twin model is used to implement the target service.

2. The method of claim 1, wherein, The network element function model is constructed according to the network element function required to possess the network element capability, and comprises: For each sub-capability, a corresponding network element function model is constructed according to a network element function required to possess the sub-capability.

3. The method according to any one of claims 1-2, characterized in that, The network element function comprises at least one hardware configuration function and at least one network configuration function; different hardware configuration functions are independent of each other, and different network configuration functions are independent of each other.

4. The method of claim 1, wherein, The method further comprises: According to the network element function, an execution instruction required to possess the network element function is queried in an instruction library; the instruction library stores instruction sets corresponding to different providers, and the instruction sets are determined according to instruction documents.

5. The method of claim 1, wherein, The network element slice model, the network element function model and the network element instruction model are assembled to obtain a digital twin model, and comprise: The network element slice model, the network element function model and the network element instruction model are respectively subjected to integrity verification; According to the service demand of the target service, model actions are added to the network element slice model, the network element function model and the network element instruction model which pass the integrity verification; The network element slice model, the network element function model and the network element instruction model to which the model actions are added are assembled to obtain a digital twin model.

6. The method of claim 5, wherein, The network element slice model, the network element function model and the network element instruction model to which the model actions are added are assembled to obtain a digital twin model, and comprise: The network element instruction model to which the model actions are added is associated to the network element function model to which the model actions are added to obtain an associated network element function model; The associated network element function model is associated to the network element slice model to which the model actions are added; The associated network element slice model is taken as the digital twin model.

7. A twin model construction apparatus characterized by comprising: The apparatus comprises: A slice construction module is configured to, in the case that a digital twin demand for a target service is acquired, determine a target network element type required to possess a network element capability required to implement the target service according to the network element capability; and construct a network element slice model by using a slice model construction mode corresponding to the target network element type; the network element capability comprises at least two independent sub-capabilities, and each sub-capability corresponds to a target network element type. A function construction module is configured to construct a network element function model according to a network element function required to possess the network element capability. An instruction construction module is configured to construct a network element instruction model according to an execution instruction required to possess the network element function. A twin model construction module is configured to assemble the network element slice model, the network element function model and the network element instruction model to obtain a digital twin model, wherein the digital twin model is configured to implement the target service.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6. The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

Images