Twin configuration method, storage medium, electronic device and product

Abstract

Embodiments of the present disclosure provide a twin configuration method, a storage medium, an electronic device and a product. The method comprises: a network digital twin management service producer constructs a twin on the basis of a twin creation request sent by a network digital twin management service consumer and a twin atom model in a twin repository; and the network digital twin management service producer configures the twin on the basis of data collected from at least one of a managed object, a data producer, and a knowledge producer, wherein the twin creation request comprises at least one of the following: a twin construction requirement, a twin data requirement, and a twin monitoring requirement.

Description

Twin configuration method, storage medium, electronic device and product

[0001] Cross-reference of related disclosures

[0002] The present disclosure is based on the Chinese patent publication 2024113982295 with the title of “Twin configuration method, storage medium, electronic device and product” filed on September 30, 2024, and claims priority to the patent publication, the disclosure of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0003] Embodiments of the present disclosure relate to the field of communication, in particular, to a twin configuration method, a storage medium, an electronic device and a product. BACKGROUND

[0004] Digital twin is a technology related to system automation that is attracting more and more attention. A digital twin object is a virtual replica of a real-world system, i.e., a “physical” system on which operations can be performed. Network digital twin (NDT) can build a real-time mirror of a physical network, reflecting the configuration, topology, state, and other information of the network, and can perform operations such as visualization of the physical network, network optimization simulation and evaluation, verification, etc., on the physical network, to predict network behavior and trends, analyze network fault root causes, and verify solutions.

[0005] The concept and key technical requirements of digital twin network have been defined in ITU Y.3091. NDT is a network system that creates a virtual twin of a physical network entity in a digital manner and can interact with the physical network entity in real time. The digital twin network can be designed as a “three-layer three-domain double closed-loop” architecture: three layers refer to the physical network layer, the twin network layer, and the network application layer that constitute the digital twin network system; three domains refer to the data domain, the model domain, and the management domain of the twin network layer, which correspond to the data sharing warehouse, the service mapping model, and the network twin management three subsystems, respectively; “double closed loop” refers to the “inner closed loop” simulation and optimization based on the service mapping model in the twin network layer, and the “outer closed loop” control, feedback, and optimization of the network application based on the three-layer architecture.

[0006] NDT can be combined with various network management intelligent technologies to provide intelligent decision support for network management, including NDT-assisted network optimization and NDT-assisted reinforcement learning.

[0007] Regarding NDT-assisted network optimization, in the context of intelligent network operation, the consumer can only propose the network optimization target (such as KPI improvement requirement) to the producer, and the producer can use NDT technology to continuously try and update the network configuration in the digital twin environment, and finally generate the optimal configuration that meets the consumer's network optimization target, without the need to continuously try and error in the real physical network, thereby avoiding the impact on the physical network.

[0008] NDT-assisted reinforcement learning. Under the reinforcement learning mechanism, the agent needs to continuously perceive the changes in the environment, set incentives, and further execute the reinforcement learning process. However, if the inference result is directly run in the physical network environment, it is easy to have unpredictable impact on the physical network. Therefore, by means of NDT technology, the twin body monitors and synchronizes the physical network state in real time, executes the inference result in the digital twin body, and if the result is acceptable, further synchronizes to the physical network environment.

[0009] However, the current 3GPP SA5 NDT protocol does not support the above use cases and related functions, and the construction of the twin body in the related technology needs to consume a large amount of resources. SUMMARY

[0010] Embodiments of the present disclosure provide a twin body configuration method, a storage medium, an electronic device and a product.

[0011] According to one embodiment of the present disclosure, a twin body configuration method is provided, comprising: a network digital twin management service producer establishing a twin body according to a twin body creation request sent by a network digital twin management service consumer and a twin atom model in a twin body warehouse; and the network digital twin management service producer configuring the twin body according to data collected from at least one of a managed object, a data producer and a knowledge producer; wherein the twin body creation request comprises at least one of the following: twin body group establishment requirement, twin body data requirement and twin body monitoring requirement.

[0012] According to another embodiment of the present disclosure, a computer readable storage medium is also provided, which stores a computer program, wherein the computer program is configured to execute the steps in the above method embodiments when running.

[0013] According to another embodiment of the present disclosure, an electronic device is also provided, which comprises a memory and a processor, the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in the above method embodiments.

[0014] According to still another embodiment of the present disclosure, a computer program product is also provided, comprising a computer program which, when executed by a processor, implements the steps of the above method embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0015] FIG. 1 is a hardware structure block diagram of a computer terminal of a twin configuration method according to an embodiment of the present disclosure;

[0016] FIG. 2 is a network architecture diagram of a twin configuration method according to an embodiment of the present disclosure;

[0017] FIG. 3 is an AI / ML operation workflow diagram according to an embodiment of the present disclosure;

[0018] FIG. 4 is a flowchart of a twin configuration method according to an embodiment of the present disclosure;

[0019] FIG. 5 is a general flowchart of a twin configuration method according to an embodiment of the present disclosure;

[0020] FIG. 6 is a flowchart of a twin configuration method according to scenario embodiment one of the present disclosure;

[0021] FIG. 7 is a flowchart of a twin configuration method according to scenario embodiment two of the present disclosure;

[0022] FIG. 8 is a flowchart of a twin configuration method according to scenario embodiment three of the present disclosure;

[0023] FIG. 9 is a flowchart of a twin configuration method according to scenario embodiment four of the present disclosure. DETAILED DESCRIPTION

[0024] Embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence.

[0026] The method embodiments provided in the embodiments of the present disclosure can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking a computer terminal as an example, FIG. 1 is a hardware structure block diagram of a computer terminal for a twin configuration method according to an embodiment of the present disclosure. As shown in FIG. 1, the computer terminal can include one or more (only one is shown in FIG. 1) processors 102 (the processor 102 can include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 configured to store data, wherein the computer terminal can further include a transmission device 106 configured to have a communication function and an input and output device 108. Those skilled in the art can understand that the structure shown in FIG. 1 is only schematic, which does not limit the structure of the computer terminal. For example, the computer terminal can further include more or less components than those shown in FIG. 1, or have a different configuration from that shown in FIG. 1.

[0027] The memory 104 can be configured to store computer programs, for example, software programs of application software and modules, such as a computer program corresponding to the twin configuration method in the embodiments of the present disclosure. The processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, that is, implements the above-mentioned method. The memory 104 can include a high-speed random access memory, and can further include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory 104 can further include a memory remotely arranged with respect to the processor 102, which can be connected to the computer terminal through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0028] The transmission device 106 is configured to receive or send data via a network. Specific examples of the network can include a wireless network provided by a communication provider of the computer terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, RF) module, which is configured to communicate with the Internet in a wireless manner.

[0029] Embodiments of the present disclosure can run on the network architecture shown in FIG. 2. As shown in FIG. 2, the network architecture includes a business support system (BSS), a cross domain management function unit (CD-MnF), a domain management function unit (Domain-MnF), and a network element (NE). The cross domain management function unit is configured to manage one or more domain management function units. The domain management function unit can be configured to manage one or more network elements.

[0030] The business support system is oriented to a communication service, and is configured to provide charging, settlement, accounting, customer service, business, network monitoring, communication service lifecycle management, service intent translation, and the like. The business support system can be an operation system of an operator, or a vertical OT system.

[0031] The cross-domain management function unit is also called a network management function unit (NMF), which can be a network management system (NMS), a network management service producer (MnS Producer), a network management service consumer (MnS Consumer), a network function management service consumer (NFMS_C), and the like. The cross-domain management function unit provides one or more of the following management functions or management services: network lifecycle management, network deployment, network fault management, network performance management, network configuration management, network assurance, network optimization function, and translation of the network intent (Intent-CSP) from a communication service provider. The network referred to in the above management functions or management services can include one or more network elements or sub-networks, or a network slice. That is, the network management function unit can be a network slice management function unit (NSMF), or a cross-domain management data analysis function unit (MDAF), or a cross-domain self-organization network function (SON Function), or a cross-domain intent-driven management function unit (Intent-Driven Management Service, Intent Driven MnS), or a cross-domain closed loop function unit (Close Control Loop Management Service).

[0032] The domain management function unit is also called a network subnet management function (NSMF) or an element management function. It can be a wireless automation engine (MAE), an element management system (EMS), a network function management service provider (NFMS_P), a network slice subnet management function (NSSMF), a domain management data analysis function (Domain MDAF), a domain self-organization network function (SON Function), a domain intent management function, or a cross-domain closed-loop function (Close Control Loop Management Service), an MnS Producer, an MnS Consumer, and other element management entities. The domain management function unit can be classified in the following ways, including: by network type, which can be classified into a radio access network (RAN) domain management function (RAN domain MnF), a core network domain management function (CN domain MnF), a transport network domain management function (TN domain MnF), and the like. It should be noted that the domain management function unit can also be a certain domain network management system, which can manage one or more of the access network, the core network, or the transport network; by administrative region, which can be classified into a domain management function unit of a certain area, such as an A city domain management function unit, a B city domain management function unit, and the like.The domain management function unit provides one or more of the following functions or management services: lifecycle management of a sub-network or a network element, deployment of a sub-network or a network element, fault management of a sub-network or a network element, performance management of a sub-network or a network element, assurance of a sub-network or a network element, optimization function of a sub-network or a network element, and translation of an intent from a network operator (Intent-NOP) of a sub-network or a network element, etc. The sub-network herein includes one or more network elements. The sub-network can also include a sub-network, i.e., one or more sub-networks form a larger sub-network. The sub-network herein can also be a network slice sub-network.

[0033] A network element is an entity providing network services. The network element includes a core network element, a radio access network element, or a transport network element, etc. Specifically, the core network element can include, but is not limited to, an access and mobility management function (AMF) entity, a session management function (SMF) entity, a policy control function (PCF) entity, a network data analysis function (NWDAF) entity, a network repository function (NRF), a gateway, etc. The radio access network element can include, but is not limited to, various types of base stations (e.g., a generation node B (gNB), an evolved node B (eNB), a central unit control panel (CUCP), a central unit (CU), a distributed unit (DU), a central unit user panel (CUUP), etc.). In the present disclosure, a network function (NF) is also referred to as a network element (NE). The network element can provide one or more of the following management functions or management services: lifecycle management of the network element, deployment of the network element, fault management of the network element, performance management of the network element, assurance of the network element, optimization function of the network element, and translation of an intent of the network element, etc.

[0034] Management services. SA5 defines four categories of management services (MnSType), including ProvMnS, FaultSupervisionMnS, StreamingDataReportingMnS, and FileDataReportingMnS. When MnSType is ProvMnS, MnsCapability includes MANAGEMENT_DATA_CONTROL, FAULT_MANAGEMENT, FILE_MANAGEMENT, NR_PROVISIONING, 5GC_PROVISIONING, NETWORK_SLICING_PROVISIONING, EDGE_COMPUTING_PROVISIONING, AI / ML_MANAGEMENT, MDA, SON_POLICY, RANSC_MANAGEMENT, INTENT_DRIVEN_MANAGEMENT, MNS_REGISTRY_AND_DISCOVERY, COMMUNICATION_SERVICE_ASSURANCE, NSOEU, MSAC_MANAGEMENT, CCL.

[0035] As shown in FIG. 3, the embodiments of the present disclosure also involve training, simulation, deployment, and inference stages. The training stage includes ML training and ML testing. The simulation stage includes ML simulation. The deployment stage includes ML entity loading. The inference stage includes AI / ML inference.

[0036] ML training: Training of one or a group of ML models, including initial training and retraining. It also includes validation of ML entities to assess the performance of the ML entities when executed on training data and validation data. If the validation results are not as expected (e.g., variance is not acceptable), the ML models associated with the entity need to be retrained. ML model training is the initial stage of the workflow.

[0037] ML testing: Testing of validated ML entities to assess the performance of the trained ML models when executed on test data. If the test results meet expectations, the ML entity can proceed to the next stage, otherwise the ML models associated with the entity can need to be retrained.

[0038] ML simulation: Running the ML entity for inference in a simulation environment. The purpose is to evaluate the inference performance of the ML entity in the simulation environment before applying the ML entity to the target network or system.

[0039] It should be noted that the simulation stage is optional and can be skipped in the AI / ML operation workflow.

[0040] ML entity loading: the process of making trained ML entities available to target AI / ML inference functions (also known as atomic operation series). In some cases, a deployment phase can not be needed, for example when the training function and inference function are co-located.

[0041] AI / ML inference: performing inference using trained ML entities by AI / ML inference functions.

[0042] Building an NDT system requires the use of the following three types of interfaces:

[0043] (1) Twin southbound interface: includes data collection interface and control delivery interface between twin network layer and physical network layer. The data collection interface is responsible for completing the data collection of the data sharing warehouse of the twin network layer, and the control delivery interface is responsible for delivering the control instructions after the simulation verification of the service mapping model to the network elements of the physical network layer.

[0044] (2) Twin northbound interface: includes intent translation interface and capability invocation interface between network application layer and twin network layer. The network application layer can pass the application layer intent to the twin network layer through the intent translation interface, providing abstracted demand input for the function model.

[0045] (3) Twin internal interface: includes a cluster of interfaces such as the interface between the internal data warehouse of the twin network layer and the function model, the interface between the function model and the digital twin management, and the interface between the function models.

[0046] Network large model, usually refers to large machine learning or deep learning models applied to telecommunications networks. Network large models need to be trained on massive data sets to learn patterns and features in the data. Through pre-training on large-scale general data sets and fine-tuning on specific tasks, network large models can adapt to different application scenarios, providing multiple capabilities for telecommunications networks, mainly including the following aspects:

[0047] Intelligent operation and maintenance: Network large models can analyze and predict telecommunications network operation and maintenance data, enabling automated fault detection, diagnosis, and repair recommendations, thereby improving operation and maintenance efficiency and reducing manual intervention.

[0048] Situation awareness: Using big data analysis and machine learning techniques, network large models can monitor network status in real time, predict network traffic and usage patterns, and provide decision support for network management and optimization.

[0049] Customer service optimization: By understanding customer inquiries and needs, network large models can provide more personalized and efficient customer service, including intelligent customer service and automated problem solving.

[0050] Network planning and construction: Network large models can assist in network planning and construction, by analyzing historical data and predicting future trends, helping operators optimize network layout and resource allocation.

[0051] Automated decision-making: Based on deep learning models, network large models can simulate complex decision-making processes, providing data-driven decision support for telecom operators.

[0052] Network optimization and maintenance: In the event of network problems or emergencies, network large models can quickly provide solutions and emergency measures to ensure network stability and reliability. In terms of wireless network optimization, network large models can analyze wireless signal coverage and quality, providing optimization suggestions to improve user service quality.

[0053] In this embodiment, a twin configuration method is provided, and FIG. 4 is a flowchart of the twin configuration method according to an embodiment of the present disclosure. As shown in FIG. 4, the flow includes the following steps:

[0054] In step S402, the network digital twin management service producer assembles a twin according to a twin creation request sent by a network digital twin management service consumer and a twin atomic model in a twin warehouse.

[0055] In step S404, the network digital twin management service producer configures the twin according to data collected from at least one of a managed object, a data producer, and a knowledge producer. The twin creation request includes at least one of the following: twin assembly requirements, twin data requirements, and twin monitoring requirements.

[0056] It should be noted that the managed object is an entity managed in the network, such as a network device, a base station, a core network element, an AMF, a data producer providing data collection, storage, and sharing management services, and a knowledge producer providing knowledge management services. Knowledge can include historical configuration information, historical event information, and historical alarm information.

[0057] In an exemplary embodiment of the present disclosure, before the network digital twin management service producer assembles a twin according to a twin creation request sent by a network digital twin management service consumer and a twin atomic model in a twin warehouse, the network digital twin management service producer also sends a network digital twin management service knowledge query request to a knowledge producer and receives network digital twin management service knowledge sent by the knowledge producer in response to the knowledge query request.

[0058] In an exemplary embodiment of the present disclosure, the network digital twin management service producer assembles a twin according to a twin creation request sent by a network digital twin management service consumer, a twin atomic model in a twin warehouse, and network digital twin management service knowledge.

[0059] In an example embodiment of the present disclosure, the network digital twin management service producer assembles the twin according to the twin creation request sent by the network digital twin management service consumer and the network digital twin management service knowledge.

[0060] In an example embodiment of the present disclosure, after the network digital twin management service producer configures the twin according to the data collected from the managed object, the data producer and the knowledge producer, the network digital twin management service producer further sends a twin creation report to the network digital twin management service consumer to indicate the success of the twin creation, wherein the twin creation report includes at least one of the following: twin atomic model information, used to indicate the component information in the twin; and twin capability information, used to indicate the supported capabilities of the twin.

[0061] In an example embodiment of the present disclosure, after the network digital twin management service producer sends the twin simulation report to the network digital twin management service consumer, the network digital twin management service producer further receives a twin visual presentation request sent by the network digital twin management service consumer, wherein the visual presentation request is used to request at least one of the following: a visual presentation form and visual presentation information; and the network digital twin management service producer sends a twin visual presentation report to the network digital twin management service consumer according to the twin visual presentation request.

[0062] In an example embodiment of the present disclosure, after the network digital twin management service producer sends the twin simulation report to the network digital twin management service consumer, the network digital twin management service producer further receives a twin visual presentation request sent by the network digital twin management service consumer, wherein the visual presentation request is used to request at least one of the following: a visual presentation form and visual presentation information; and the network digital twin management service producer sends a twin visual presentation report to the network digital twin management service consumer according to the twin visual presentation request.

[0063] In an example embodiment of the present disclosure, the twin assembly requirement includes at least one of the following: twin capability information, used to indicate the requested twin type and capability; twin assembly method, used to indicate the assembly method of the twin; and twin assembly range, used to indicate the twin range of the twin.

[0064] In an example embodiment of the present disclosure, the twin data requirement includes at least one of the following: data source, used to indicate the source of the twin data; and data collection and synchronization control, used to control the data collection and synchronization of the twin.

[0065] In an example embodiment of the present disclosure, the twin monitoring requirements include at least one of the following: a monitoring index indicating a requested index to be monitored by the twin; a monitoring event indicating an event to be monitored by the twin.

[0066] In an example embodiment of the present disclosure, before the network digital twin management service producer sets up the twin, the network digital twin management service producer further receives a twin creation request generated by the network digital twin management service consumer according to an MDA request, wherein the MDA request is used to request to obtain an optimal strategy or an optimal configuration for the network.

[0067] In one embodiment, the optimal strategy is a network energy saving strategy, and the optimal configuration is a network energy saving configuration.

[0068] In an example embodiment of the present disclosure, after the network digital twin management service producer configures the twin, the network digital twin management service producer further receives a twin simulation request sent by the network digital twin management service consumer, wherein the twin simulation request includes at least a network optimization target parameter; the network digital twin management service producer performs network optimization simulation in a simulation environment according to the twin simulation request, and sends a twin simulation report to the network digital twin management service consumer according to a network optimization result; wherein the twin simulation report includes an optimal network configuration.

[0069] In one embodiment, the optimal network configuration is a best network configuration to achieve the network optimization target, or a plurality of alternative configuration schemes.

[0070] In one embodiment, the network optimization target parameter indicates a network index to be optimized, such as energy consumption, throughput, etc., which can be one or more indexes.

[0071] In an example embodiment of the present disclosure, the network digital twin management service producer performs intent feasibility check simulation in a simulation environment according to the twin simulation request sent by the network digital twin management service consumer, and sends a twin simulation report to the network digital twin management service consumer according to an intent feasibility check result; wherein the twin simulation report includes the intent feasibility check result, and the intent feasibility check result includes feasibility or unfeasibility, and the twin simulation request includes at least an intent parameter.

[0072] In one embodiment, the intent parameter includes at least one of the following: an intent expectation, an intent context, an intent expectation object, an intent expectation context, and an intent expectation index, and the intent parameter is used to indicate a target and condition that the consumer expects the network to achieve.

[0073] In the example embodiment of the present disclosure, in the case that the intention feasibility check result is unfeasible, the first intention modification suggestion and the intention unfeasible reason are added to the twin simulation report, wherein the first intention modification suggestion includes at least one of the following: a modification range of the intention expected indicator and a newly added restriction condition in the intention context; in the case that the intention feasibility check result is feasible, the second intention modification suggestion and the evaluation information are added to the twin simulation report, wherein the second intention modification suggestion at least includes the intention expected indicator in the optimized intention parameter, and the evaluation information includes at least one of the following: the affected entity and the network performance indicator.

[0074] In the example embodiment of the present disclosure, before the network digital twin management service producer assembles the twin, the network digital twin management service producer further receives a twin creation request generated by the network digital twin management service consumer according to a reinforcement learning request, wherein the reinforcement learning request is used to request the network digital twin management service consumer to perform reinforcement learning simulation.

[0075] In the example embodiment of the present disclosure, after the network digital twin management service producer sends the twin creation report indicating the success of the twin creation to the network digital twin management service consumer, the network digital twin management service producer further receives a twin simulation request sent by the network digital twin management service consumer, the twin simulation request is used to request the network digital twin management service producer to perform inference result execution simulation; the network digital twin management service producer performs inference result execution simulation, and sends a twin simulation report to the network digital twin management service consumer according to the simulation result, wherein the twin simulation report includes at least one of the following: monitoring indicators, monitoring events and abnormal situation information; the network digital twin management service consumer sets incentive information according to the twin simulation report, and determines whether to execute the current inference result in the physical network.

[0076] In the example embodiment of the present disclosure, after the network digital twin management service producer sends the twin simulation report to the network digital twin management service consumer according to the execution result, the network digital twin management service producer further requests to perform data synchronization, wherein the data synchronization is generated after the inference result execution of the managed entity in response to the inference result execution request sent by the network digital twin management service consumer to the managed entity.

[0077] In the example embodiment of the present disclosure, before the network digital twin management service producer assembles the twin, the network digital twin management service producer further receives a twin creation request generated by the network digital twin management service consumer according to a federated learning request, wherein the federated learning request is used to request the network digital twin management service consumer to perform federated learning.

[0078] In the example embodiments of the present disclosure, the federated learning request comprises at least one of: a client selection requirement, used to indicate the selection requirement of the client, wherein the client selection requirement comprises at least one of: a training time requirement and a training data requirement; a client contribution evaluation strategy, used to indicate the evaluation criteria and strategy of evaluating the contribution of each client in the federated learning process, wherein the client contribution evaluation strategy comprises at least one of: a training data-based strategy, a training time-based strategy, a training energy consumption-based strategy, and a training computing power-based strategy.

[0079] In the example embodiments of the present disclosure, after the network digital twin management service producer sends the twin creation report for indicating the success of the twin creation to the network digital twin management service consumer, the network digital twin management service producer further comprises: performing twin simulation according to the twin simulation request sent by the network digital twin management service consumer, and sending a twin simulation report to the network digital twin management service consumer, so that the network digital twin management service consumer determines a training scheme and performs federated learning and sends a federated learning report to the AIML consumer, wherein the federated learning report comprises at least one of: the contribution of each client in the selected training scheme and the recommended server node or client node; wherein the twin simulation report comprises at least one of: the best training scheme, multiple training schemes, the contribution of each client in each training scheme, and the recommended server node or client node.

[0080] In the example embodiment of the present disclosure, before the network digital twin management service producer groups the twin, the network digital twin management service producer further comprises: sending a network digital twin management service registration request to a management service registration and discovery producer, wherein the network digital twin management service registration request comprises: a network digital twin management service producer identifier, a management service type, and a management service capability; receiving a first notification message sent by the management service registration and discovery producer, wherein the first notification message is used to confirm whether the management service registration is successful; sending a network digital twin management service producer discovery request to the management service registration and discovery producer, wherein the network digital twin management service producer discovery request is used to indicate the management service type and the management service capability; receiving a second notification message sent by the management service registration and discovery producer, wherein the second notification message comprises an identifier and an address of the network digital twin management service producer; receiving a network digital twin management service capability information query request sent by the network digital twin management service consumer, wherein the network digital twin management service information query request comprises network digital twin management service producer capability information; wherein the network digital twin management service producer capability information comprises at least one of: network digital twin management service capability type information, used to indicate the capability supported by the twin; network digital twin management service state information, used to indicate the current state of the twin; and network digital twin management service available time, used to indicate the available time of the twin.

[0081] In the example embodiment of the present disclosure, the network digital twin management service registration request and the network digital twin management service producer discovery request further comprise network digital twin management service producer capability information.

[0082] Through the above-mentioned embodiments of the present disclosure, since the network digital twin management service producer receives a twin creation request, the twin creation request comprises at least one of: twin grouping requirements, twin data requirements, and twin monitoring requirements, the network digital twin management service producer generates a twin by combining the twin creation request and the twin atomic model in the twin repository, instead of directly creating a twin. Based on the generated twin, the network digital twin management service producer configures the twin according to the data collected from at least one of the managed object, the data producer, and the knowledge producer. Therefore, the problem that a large amount of resources are consumed when constructing a twin in the related art can be solved, and the effect of generating a twin using fewer resources is achieved.

[0083] Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software on a general hardware platform required, and of course can also be implemented by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present disclosure can be embodied in the form of a software product in essence or in the form of a part of the prior art that contributes to the present disclosure. The computer software product is stored in a storage medium (such as a ROM / RAM, a magnetic disk, or an optical disk) and includes a number of instructions for causing an end device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the method described in each embodiment of the present disclosure.

[0084] In order to facilitate the understanding of the technical solutions provided by the disclosed embodiments, the following will be described in conjunction with specific scene embodiments.

[0085] FIG. 5 is a general flowchart of a twin configuration method according to an embodiment of the present disclosure. The general flowchart mainly describes a general flowchart applicable to all scenarios, including NDT management service registration, NDT management service discovery, NDT management service capability query, etc. As shown in FIG. 5, the flowchart includes the following steps:

[0086] Step S501, the NDT MnS Producer sends an NDT management service registration request to the MnS Registration / Discovery Producer, and the request includes the identity (Distinguish name, DN) of the NDT Producer, the management service type (mnsType=ProvMnS), the management service capability (mnsCapability=NDT), and optionally includes the management service capability information (mnsCapabilityInfo, when mnsCapability is NDT, it indicates the specific capabilities supported by NDT, such as supported NDT CapabilityType-signaling storm simulation, supported visualization mode, etc.).

[0087] The MnS Registration / Discovery Producer sends a notification to the NDT MnS Producer to confirm whether the management service registration is successful.

[0088] Step S502, the NDT MnS Consumer sends an NDT management service producer discovery request to the MnS Registration / Discovery Producer, indicating the management service type (mnsType=ProvMnS) and the management service capability (mnsCapability=NDT) in the request, and optionally including the management service capability information (NDTCapabilityType-signaling storm simulation).

[0089] The MnS Registration / Discovery Producer sends a notification to the NDT MnS Consumer, which contains the identification and address of the NDT MnS Producer.

[0090] When the management service capability information is not included in steps S501 and S502, the Consumer performs step S503.

[0091] Step S503, the NDT MnS Consumer sends an NDT capability information query request to the NDT MnS Producer, which contains specific capability information of the NDT Producer, such as NDTCapabilityType (indicating specific capabilities supported by the twin, such as signaling storm simulation, policy verification, etc.), NDTState (indicating the current state information of the twin, such as "available", "in simulation", "unavailable", etc.), and NDTAvailableTime (indicating the specific available time of the twin).

[0092] It should be noted that the completion of the above general process is a prerequisite for the implementation of the following scenario embodiment.

[0093] Scenario Embodiment One

[0094] FIG. 6 is a flowchart of a twin configuration method according to the scenario embodiment one of the present disclosure, in which the NDT MnS Consumer is an MDAF, the NDT assists the MDAF in generating a recommended scheme, and the NDT MnS Producer registration / discovery / capability query process has been completed, as shown in FIG. 6, which includes the following steps:

[0095] Step S601, the MDA Consumer sends an MDA request to the MDAF, which gives a network energy saving policy or network energy saving configuration for a certain area, including network elements and cells entering the energy saving state, and the expected energy saving target.

[0096] Step S602, the MDAF sends a twin creation request to the NDT MnS Producer as the NDT MnS Consumer, requesting the NDT Producer to give the best network energy saving strategy or network energy saving configuration. The twin creation request contains at least one of the following: twin group building requirement, twin data requirement, and / or twin monitoring requirement.

[0097] The twin group building requirement is used to indicate the requirement of the Consumer for the twin configuration, and contains the following parameters: twin capability information, twin group building method, and twin group building range.

[0098] The twin capability information indicates the requested twin type and capability, and can include the following forms: twin application, network element twin, network twin, service twin, etc.; twin capability, perception, analysis (prediction), decision, etc.; and twin category, policy verification, fault injection, signaling storm simulation, etc.

[0099] The twin group building method is used to indicate the creation method of the twin. It should be noted that when a new twin is requested to be created, it can be simulation, simulation, simulation+simulation; when an existing twin is requested to be updated / activated, it can be the identification of the existing twin.

[0100] The twin group building range is used to indicate the twin range of the twin. The twin range includes environment information, twin range, support information, and twin atomic model information. The environment information includes geographical area, time period, and specific conditions (such as user traffic, etc.); the twin range includes network element twin, network twin, and service twin; the support information includes meteorological conditions, natural disasters, and specific scenarios (concerts, etc.); and the twin atomic model information includes twin atomic model category and twin atomic model identification. The twin atomic model category can be environment category (channel model, 3D environment model, geometric model), device category (UE twin model, device twin model, network element twin model, base station twin model, site twin model, etc.), user category (point category [UE location, which can be indoor / outdoor model, indoor 3D location, outdoor positioning]; line category [individual trajectory, user portrait, social relationship], surface category [group migration, traffic distribution, spatiotemporal prediction, etc.]), network category (network topology model; process category model, RSRP, SINR, handover behavior, etc., result category model, such as coverage KPI, capacity KPI, etc.), and service category (process category model, service generation, service scheduling, service routing, etc.; result category model, KPI model, KQI model, user experience scoring model, business value model, etc.). The twin atomic model identification can be the identification of the twin atomic model itself, or the identification of the network entity that needs to be twinned. The twin atomic model can also be a twin.

[0101] Twin data requirement, Consumer's requirement for twin data collection and synchronization, including the following parameters: data source, data collection and synchronization control, twin monitoring requirement.

[0102] Data source is used to indicate the source of twin data, which can include the following parameters: managed entity identifier (twin network entity identifier), indicating that real-time / historical data needs to be collected from these entities; data source identifier, identifier of Data Producer, Data Producer stores historical / future data, or real-time data collected from managed entities; knowledge source identifier, identifier of Knowledge Producer, Knowledge Producer stores various network knowledge, such as configuration information of historical NDT instances, behavior of each twin atomic model in NDT instances, and twin output indicator range.

[0103] Data collection and synchronization control can include the following parameters: data collection control information, used to control network data collection, including historical / real-time / future data collection time, frequency, data volume, etc.; data synchronization control information, used to control twin data synchronization, historical / real-time / future data synchronization time, frequency, data volume, etc.

[0104] Twin monitoring requirement indicates the Consumer's requirement for twin state monitoring, including the following parameters: monitoring KPI, indicating the requested twin monitoring indicators; monitoring event, indicating the twin monitoring events.

[0105] In this scenario embodiment, the NDT Consumer requests the NDT Producer to give the best network energy saving strategy or network energy saving configuration, and the following gives a specific example:

[0106] Twin building requirement: twin capability information, twin category-network optimization-best network energy saving strategy; twin building method, simulation+simulation; twin building range: environment information: city A; twin range: network twin; support information: rainy day, large sports event; twin atomic model information, twin atomic model identifier, network entity identifier that needs to be twinned.

[0107] Twin data requirement: data source: managed entity identifier; data source identifier, identifier of Data Producer; knowledge source identifier, identifier of Knowledge Producer; data collection and synchronization control: data collection control information, data collection time window; data synchronization control information, twin data synchronization frequency.

[0108] Twin monitoring requirement, indicates the Consumer's requirement for twin status monitoring, contains the following parameters: monitoring KPI, energy consumption indicator; monitoring event, switching event;

[0109] Note: the above twin creation request parameters are also applicable to the twin update / activation scenario.

[0110] Step S603a (optional), the NDT MnS Producer sends a knowledge query request to the Knowledge Producer, and the Knowledge Producer feeds back the NDT-related knowledge.

[0111] Step S603b (optional), the NDT MnS Producer assembles the twin according to the received twin creation request, and / or the NDT-related knowledge obtained from the Knowledge producer; the NDT MnS Producer can also select a twin atom model from the NDT Repository according to the twin atom model information, to construct the twin.

[0112] Step S604a: twin data synchronization, the NDT MnS Producer collects real-time data from the managed object, and configures the twin according to the real-time data.

[0113] Step S604b: twin data synchronization, the NDT MnS Producer collects historical data from the Data Producer, and configures the twin according to the historical data.

[0114] Step S604c: twin data synchronization, the NDT MnS Producer collects knowledge data from the Knowledge Producer, and configures the twin according to the knowledge data.

[0115] It should be noted that in actual application, at least one of steps S604 / step S604 / step S604 can be used.

[0116] Step S605: the NDT MnS Producer sends a twin creation report to the NDT MnS Consumer, indicating that the twin creation is successful, and can also include one of the following information: twin atom model information, indicating the specific component information in the twin; twin capability information.

[0117] Step S606: the NDT MnS Consumer sends a twin simulation request to the NDT MnS Producer, containing at least one of the following information: twin monitoring requirement and twin simulation requirement.

[0118] Twin monitoring requirement, indicating the requirement of the Consumer on the monitoring of the twin status, containing the following parameters: monitoring indicators, indicating the requested indicators that the twin needs to monitor; monitoring events, indicating the events that the twin needs to monitor.

[0119] Twin simulation requirement, indicating the requirement of the Consumer on the simulation process and results of the twin, containing the following parameters: simulation process control, indicating the simulation execution frequency, executed events and conditions, execution time; start, activate, pause and terminate of the simulation process; twin category, network optimization-optimal network energy saving strategy; simulation results, indicating the simulation results that need to be covered in the twin report, which can be specific configuration parameters; number of candidate solutions; solution recommendation reason; potential risk of solution, etc.

[0120] Step S607: The NDT MnS Producer automatically updates its components or configuration parameters according to the received twin simulation request, maximizes the attempt to approach the optimization target.

[0121] Step S608: The NDT MnS Producer sends a twin simulation report to the NDT MnS Consumer. The twin simulation report contains at least one of the following parameters: monitoring indicators, energy consumption related indicators; monitoring events, such as handover events; monitoring events, monitoring events indicated in the twin monitoring requirement; abnormal situation information, indicating unexpected situations, such as affected indicators (monitoring KPIs not indicated in the creation request), possible event abnormalities (such as device failure, UE access failure, single cell traffic load too large, etc.), affected network entities (base stations, network elements, network management, devices, etc.); optimal configuration information, indicating the optimal configuration of the network, such as the optimal configuration set (one or more configuration solutions) verified by the NDT simulation, including configuration solutions, potential risks of solutions (high handover failure rate), reasons for solution recommendation (small energy consumption, energy consumption value is xx kWH), etc.

[0122] Step S609: The NDT MnS Consumer sends a twin visualization presentation request to the NDT MnS Producer, containing the following parameters: visualization presentation form, text, animation; visualization presentation information, such as twin atom model category, listing only the component categories in the twin; twin atom model identifier, listing the identifiers of the twin atom models in the twin.

[0123] Step S6010: The MLT Producer sends a twin visualization presentation report to the MLT Consumer according to the twin visualization presentation request, containing the visualization presentation information indicated in Step 8.

[0124] Step S6011: The MDAF generates a MDA report according to the received twin simulation report and sends it to the MDA Consumer.

[0125] Scenario Embodiment Two

[0126] FIG. 7 is a flowchart of a twin configuration method according to scenario embodiment two of the present disclosure, in which the NDT MnS Consumer is an Intent Driven Management Service (IDMS) Producer, and the NDT-assisted intent feasibility check, as shown in FIG. 7, includes the following steps:

[0127] Step S701: The IDMS Consumer sends an Intent request, requesting it to verify the feasibility of the intent.

[0128] Step S702: The IDMS Producer sends a twin creation request to the NDT MnS Producer as the NDT MnS Consumer, and the request contains intent parameters (intent expectation, intent context, intent expectation object, intent expectation context, intent expectation index), such as a business assurance intent, wherein the intent expectation object is a network entity in a certain area; the intent context is the assurance time; and the intent expectation index is the assurance index, such as the number of user accesses, user download rate, etc.

[0129] Step S703: The IDMS Producer performs business assurance twin orchestration and creation according to the intent parameters in the twin creation request.

[0130] Step S704: The NDT MnS Producer collects data and synchronizes twin data.

[0131] Step S705: The NDT MnS Producer sends a twin creation report to the NDT MnS Consumer.

[0132] Step S706: The IDMS Producer sends a twin simulation request, and the request contains intent-related parameters.

[0133] Step S707: The NDT MnS Producer performs an intent feasibility check in the simulation environment.

[0134] Step S708: The NDT MnS Producer sends a twin simulation report to the NDT MnS Consumer, which contains the intent feasibility check result (feasible / feasible).

[0135] When the feasibility check result is not feasible, the twin simulation report can also include recommendation information, including intent modification suggestions, such as modification range of intent expected indicators, addition of restrictions in intent context, etc.; and recommendation reasons, such as reasons for infeasible intent, such as inability to achieve guarantee indicators, etc.

[0136] When the feasibility check result is feasible, the twin simulation report can also include recommendation information, including intent modification suggestions (further optimization of intent expected indicators in intent parameters); and evaluation information, including at least one of the following: affected entities, network performance indicators, and network performance indicators.

[0137] Step S709: The IDMS Producer sends an Intent report, which includes the feasibility check result, intent modification suggestions, and reasons for infeasible intent, etc.

[0138] Scenario embodiment three

[0139] FIG. 8 is a flowchart of a twin configuration method according to scenario embodiment three of the present disclosure, in which the NDT MnS Consumer is an AIML RL Producer, as shown in FIG. 8, the flow includes the following steps:

[0140] Step S801: The AIML Consumer sends a reinforcement learning request, requesting the Producer to perform reinforcement learning. The reinforcement learning request includes at least one of the following information:

[0141] Simulation environment indication information, indicating that reinforcement learning is performed in a simulation environment, or indicating that reinforcement learning is performed in a twin;

[0142] Twin group building requirements, indicating the configuration of a specific simulation environment. For example, network entities that need to be included in the simulation environment can include twin atomic model information.

[0143] Steps S802-S805: Same as steps S602-S605 of scenario embodiment one.

[0144] Step S806: The AIML Producer performs initial model loading, performs reasoning, and generates reasoning results.

[0145] Step S807: The AIML Producer sends a twin simulation request to the NDT MnS Producer, requesting to execute the reasoning results and to perform reinforcement learning in a digital twin environment. The specific parameters of the twin simulation request are as described in scenario embodiment one.

[0146] Step S808: The NDT MnS Producer executes the reasoning results.

[0147] Step S809: The NDT MnS Producer sends a twin simulation report to the AIML Producer. The specific parameters of the twin simulation report are shown in Embodiment 1.

[0148] Step S8010: The AIML Producer sets incentive information according to the twin simulation report, and decides whether to execute the inference result in the physical network. The setting of the model incentive information can be performed by the AIML Producer, or can be generated by another ML model according to the twin simulation report.

[0149] Continue reinforcement learning:

[0150] Step S8011: The AIML Producer performs model update according to the incentive and twin feedback.

[0151] Step S8012: The AIML Producer requests to execute the inference result and the twin data synchronization. The inference result execution request is sent to the managed entity, and the request contains the configuration information of the managed entity. The data synchronization request is sent to the NDT MnS Producer, and the twin is requested to execute data synchronization.

[0152] Step S8013: The managed entity in the physical network executes the inference request.

[0153] Step S8014: The NDT MnS Producer executes data synchronization.

[0154] Step S8015: Return to step S806.

[0155] Execute fallback.

[0156] Step S8016: Return to step S806.

[0157] Step S8017: The AIML Producer sends a reinforcement learning report to the AIML Consumer, and the report contains the reinforcement learning record.

[0158] Scenario Embodiment Four

[0159] FIG. 9 is a flowchart of a twin configuration method according to the scenario embodiment four of the present disclosure. In this embodiment, the NDT MnS Consumer is the AIML FL Producer. As shown in FIG. 9, the flowchart includes the following steps:

[0160] Step S901: The AIML Consumer sends a federated learning request to request the Producer to perform federated learning. The federated learning request contains at least one of the following information:

[0161] The Client selects requirements, indicates the selection requirements of the Client, including training time requirements, training data requirements (training data volume, training data samples (such as slice identification, UE identification), training data features (PM, KPI)).

[0162] The Client contribution evaluation strategy indicates the evaluation criteria and strategy for evaluating the contribution of each Client in the federated learning process, which can include: a training data-based strategy, such as indicating that the contribution is calculated based on the proportion of the training data volume of each Client to the total training data volume (training data of all nodes); a training time-based strategy, such as indicating that the contribution is calculated based on the proportion of the training time of each Client to the total training time (training time of all nodes); a training energy consumption-based strategy, such as indicating that the contribution is calculated based on the proportion of the training energy consumption of each Client to the total training energy consumption (training energy consumption of all nodes); a training computing power-based strategy, such as indicating that the contribution is calculated based on the proportion of the training computing power of each Client to the total training computing power (training computing power of all nodes);

[0163] Steps S902-S905: Same as steps S602-S605 of scenario embodiment one.

[0164] Step S906: The AIML Producer determines a federated learning training scheme and simulates the training of each Client in the federated learning in a twin.

[0165] Step S907: The NDT MnS Producer performs simulation.

[0166] Step S908: The NDT MnS Producer sends a twin simulation report to the AIML Producer. The specific parameters of the twin simulation report are shown in scenario embodiment one, and the twin simulation report further includes: the optimal training scheme and / or multiple training schemes, and the contribution of each Client in each scheme; recommended Server / Client nodes.

[0167] Step S909: The AIML Producer determines a training scheme and performs federated learning.

[0168] Step S9010: The AIML Producer sends a federated learning report, which includes the contribution of each Client in the selected training scheme and recommended Server / Client nodes.

[0169] Embodiments of the present disclosure also provide a computer-readable storage medium having a computer program stored therein, wherein the computer program is configured to execute the steps in any of the method embodiments described above when running.

[0170] In an example embodiment, the computer readable storage medium described above can include, but is not limited to, a U disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store computer programs.

[0171] Embodiments of the present disclosure also provide an electronic device including a memory and a processor, the memory storing a computer program, and the processor being configured to execute the computer program to perform the steps in any of the method embodiments described above.

[0172] In an example embodiment, the electronic device described above can further include a transmission device connected to the processor and an input and output device connected to the processor.

[0173] The specific examples in the present embodiment can refer to the examples described in the above embodiments and example implementations, and the present embodiment will not be described here again.

[0174] Obviously, those skilled in the art should understand that the modules or steps of the present disclosure described above can be realized by general computing devices, which can be concentrated on a single computing device or distributed on a network composed of multiple computing devices, and they can be realized by program codes executable by computing devices, so that they can be stored in storage devices and executed by computing devices, and in some cases, the steps shown or described can be executed in different order, or they can be manufactured into individual integrated circuit modules, or multiple modules or steps among them can be manufactured into a single integrated circuit module. Thus, the present disclosure is not limited to any specific combination of hardware and software.

[0175] The above only describes the preferred embodiments of the present disclosure and is not intended to limit the present disclosure. For those skilled in the art, the present disclosure can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. within the principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A twin configuration method, comprising: a network digital twin management service producer configuring a twin according to data collected from at least one of a managed object, a data producer and a knowledge producer; wherein the twin creation request comprises at least one of the following: twin configuration requirements, twin data requirements and twin monitoring requirements. the network digital twin management service producer sending a network digital twin management service knowledge query request to the knowledge producer, and receiving network digital twin management service knowledge sent by the knowledge producer in response to the knowledge query request; 2. The method of claim 1, wherein, the method further comprising the network digital twin management service producer configuring the twin according to the twin creation request sent by the network digital twin management service consumer, the twin atomic model in the twin warehouse and the network digital twin management service knowledge. the method further comprising the network digital twin management service producer configuring the twin according to the twin creation request sent by the network digital twin management service consumer and the network digital twin management service knowledge.

3. The method of claim 2, wherein, the network digital twin management service producer sending a twin creation report to the network digital twin management service consumer to indicate that the twin creation is successful; 4. The method of claim 2, wherein, wherein the twin creation report comprises at least one of the following:

5. The method of claim 1, wherein, twin atomic model information, used to indicate component information in the twin; twin capability information, used to indicate capabilities supported by the twin. the network digital twin management service producer receiving a twin simulation request sent by the network digital twin management service consumer; the network digital twin management service producer performing twin simulation in response to the twin simulation request, and sending a twin simulation report to the network digital twin management service consumer; wherein the twin simulation request comprises at least one of the following: twin monitoring requirements and twin simulation requirements; 6. The method of claim 5, wherein, wherein the twin simulation report comprises at least one of the following: monitoring indicators, monitoring events, abnormal situation information and optimal configuration information. the network digital twin management service producer sending a twin simulation report to the network digital twin management service consumer; ​ ​ ​ 7. The method of claim 6, wherein, ​ The network digital twin management service producer receives a twin visual presentation request sent by the network digital twin management service consumer, wherein the visual presentation request is used to request to obtain at least one of the following: a visual presentation form and visual presentation information; The network digital twin management service producer sends a twin visual presentation report to the network digital twin management service consumer according to the twin visual presentation request.

8. The method of claim 1, wherein, The twin composition requirement includes at least one of the following: Twin capability information, used to indicate a requested twin type and capability; Twin composition mode, used to indicate a composition mode of the twin; Twin composition range, used to indicate a twin range of the twin.

9. The method of claim 1, wherein, The twin data requirement includes at least one of the following: Data source, used to indicate a source of the twin data; Data acquisition and synchronization control, used to control data acquisition and synchronization of the twin.

10. The method of claim 1, wherein, The twin monitoring requirement includes at least one of the following: Monitoring index, used to indicate a requested monitoring index of the twin; Monitoring event, used to indicate a monitoring event of the twin.

11. The method of claim 1, wherein, Before the network digital twin management service producer composes the twin, the method further includes: The network digital twin management service producer receives a twin creation request generated by the network digital twin management service consumer according to an MDA request, wherein the MDA request is used to request to obtain an optimal strategy or optimal configuration for the network.

12. The method of claim 6 or 11, wherein, After the network digital twin management service producer configures the twin, the method further includes: The network digital twin management service producer receives a twin simulation request sent by the network digital twin management service consumer, wherein the twin simulation request includes at least a network optimization target parameter; The network digital twin management service producer performs network optimization simulation in a simulation environment according to the twin simulation request, and sends a twin simulation report to the network digital twin management service consumer according to a network optimization result; The twin simulation report includes an optimal network configuration.

13. The method of claim 6, wherein, The method further includes: The network digital twin management service producer performs intent feasibility check simulation in a simulation environment according to the twin simulation request sent by the network digital twin management service consumer, and sends a twin simulation report to the network digital twin management service consumer according to an intent feasibility check result; The twin simulation report includes the intent feasibility check result, and the intent feasibility check result includes feasibility or unfeasibility. The twin simulation request includes at least an intent parameter.

14. The method of claim 13, wherein, In the case that the intent feasibility check result is unfeasible, a first intent modification suggestion and an intent unfeasibility reason are added to the twin simulation report, wherein the first intent modification suggestion includes at least one of the following: a modification range of an intent expected index and a newly added limitation condition in an intent context; In the case that the intention feasibility check result is feasible, a second intention modification suggestion and evaluation information are added to the twin simulation report, wherein the second intention modification suggestion at least includes an intention expectation index in the optimized intention parameter, and the evaluation information at least includes one of the following: an affected entity and a network performance index.

15. The method of claim 1, wherein, Before the network digital twin management service producer assembles the twin, further comprising: The network digital twin management service producer receives a twin creation request generated by the network digital twin management service consumer according to a reinforcement learning request, wherein the reinforcement learning request is used to request the network digital twin management service consumer to perform reinforcement learning simulation.

16. The method of claim 5, wherein, After the network digital twin management service producer sends the network digital twin management service consumer a twin creation report indicating that the twin creation is successful, further comprising: The network digital twin management service producer receives a twin simulation request sent by the network digital twin management service consumer, wherein the twin simulation request is used to request the network digital twin management service producer to perform inference result execution simulation; The network digital twin management service producer performs the inference result execution simulation, and sends a twin simulation report to the network digital twin management service consumer according to the simulation result, wherein the twin simulation report includes at least one of the following: monitoring indicators, monitoring events and abnormal situation information; The network digital twin management service consumer sets incentive information according to the twin simulation report, and determines whether to execute the current inference result in the physical network.

17. The method of claim 16, wherein, After the network digital twin management service producer sends the network digital twin management service consumer a twin simulation report according to the execution result, further comprising: The network digital twin management service producer requests to perform data synchronization, which is generated after the inference result execution of the managed entity in response to the inference result execution request sent by the network digital twin management service consumer to the managed entity.

18. The method of claim 1, wherein, Before the network digital twin management service producer assembles the twin, further comprising: The network digital twin management service producer receives a twin creation request generated by the network digital twin management service consumer according to a federated learning request, wherein the federated learning request is used to request the network digital twin management service consumer to perform federated learning.

19. The method of claim 18, wherein, The federated learning request includes at least one of the following: Client selection requirements, used to indicate the selection requirements of the client, wherein the client selection requirements include at least one of the following: training time requirements and training data requirements; Client contribution evaluation strategy, used to indicate the evaluation criteria and strategy of evaluating the contribution of each client in the federated learning process, wherein the client contribution evaluation strategy includes at least one of the following: a strategy based on training data, a strategy based on training time, a strategy based on training energy consumption, and a strategy based on training computing power.

20. The method of claim 5, wherein, After the network digital twin management service producer sends the network digital twin management service consumer a twin creation report indicating that the twin creation is successful, further comprising: The network digital twin management service producer performs twin simulation according to the twin simulation request sent by the network digital twin management service consumer, sends a twin simulation report to the network digital twin management service consumer, so that the network digital twin management service consumer determines a training scheme and performs federated learning and sends a federated learning report to the AIML consumer, wherein the federated learning report includes at least one of the following: the contribution of each client in the selected training scheme and the recommended server node or client node. The twin simulation report includes at least one of the following: the best training scheme, multiple training schemes, the contribution of each client in each training scheme, and the recommended server node or client node.

21. The method of claim 1, wherein, Before the network digital twin management service producer groups the twins, the method further includes: The network digital twin management service producer sends a network digital twin management service registration request to the management service registration and discovery producer, wherein the network digital twin management service registration request includes the network digital twin management service producer identifier, the management service type, and the management service capability. The network digital twin management service producer receives a first notification message sent by the management service registration and discovery producer, and the first notification message is used to confirm whether the management service registration is successful. The network digital twin management service consumer sends a network digital twin management service producer discovery request to the management service registration and discovery producer, and the network digital twin management service producer discovery request is used to indicate the management service type and the management service capability. The network digital twin management service consumer receives a second notification message sent by the management service registration and discovery producer, and the second notification message includes the identifier and the address of the network digital twin management service producer. The network digital twin management service producer receives a network digital twin management service capability information query request sent by the network digital twin management service consumer, and the network digital twin management service information query request includes network digital twin management service producer capability information. The network digital twin management service producer capability information includes at least one of the following: Network digital twin management service capability type information, used to indicate the capability supported by the twin; Network digital twin management service state information, used to indicate the current state of the twin; Network digital twin management service available time, used to indicate the available time of the twin.

22. The method of claim 21, wherein, The network digital twin management service registration request and the network digital twin management service producer discovery request further include network digital twin management service producer capability information.

23. A computer readable storage medium having stored therein a computer program, wherein, The computer program is executed by the processor to implement the steps of the method described in any one of claims 1 to 21. 24.An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method described in any one of claims 1 to 21 when executing the computer program.

25. A computer program product comprising a computer program which, when executed by a processor, implements the steps of the method as claimed in any one of claims 1 to 21.

Images