Operation and maintenance methods and equipment for endogenous intelligence and digital twins

Abstract

A method and device for operating and maintaining endogenous intelligence and digital twins, wherein the method includes: the managed object simulates the corresponding functional body through the first DT system, obtains measurement data, and reports the measurement data to the second DT system in the operation and maintenance system, and provides data services to its own first distributed AI system; the managed object interacts with the second distributed AI system in the operation and maintenance system through the first distributed AI system, and executes the predetermined AI algorithm or predetermined task based on the information obtained from the interaction, wherein the first distributed AI system and the second distributed AI system are different parts of the distributed AI function, and the second distributed AI system and the first distributed AI system jointly execute the predetermined AI algorithm or predetermined task. The embodiment of the present invention implements an OAM system for endogenous AI, reducing the overhead of information reporting between the OAM system and the managed object.

Description

Technical Field

[0001] The present invention relates to the field of mobile communication technologies, and in particular to an operation and maintenance method and equipment for endogenous intelligence and digital twins. Background Art

[0002] Artificial intelligence (AI) in fourth-generation / fifth-generation mobile communication (4G / 5G) networks is external AI. That is, various information required by AI is reported to AI functional nodes through the network side (base station, core network) and the terminal side. AI-related processing is performed outside the network element. The AI ​​functional node collects and processes data, trains AI models, and then sends the results of AI operation or the generated policy (Policy) to the network.

[0003] Currently, AI in 4G / 5G networks is plug-in AI, running in the Operations and Maintenance (OAM) system. This presents two insurmountable challenges: 1) To make AI operation results more accurate or effective, large amounts of real-time, fine-grained measurement information must be reported to the OAM system. This approach, both in terms of cost and interoperability (interconnection of abnormal parts), is difficult to commercialize in commercial networks. 2) Due to the limitations of the transmission network connecting OAM to the network side, the effectiveness of AI on the network depends on the accuracy of the measurement data. As a result, the results of AI operation or the resulting policies may not match the needs of the network, making it difficult to reflect the benefits brought by AI to the network and thus making it difficult to realize the vision of a smart network. Summary of the Invention

[0004] At least one embodiment of the present invention provides an operation and maintenance method and device for endogenous intelligence and digital twins, realizes an operation and maintenance system for endogenous AI, and can reduce the overhead of information reporting between the operation and maintenance system and the managed objects.

[0005] According to one aspect of the present invention, at least one embodiment provides a managed object, including a first digital twin DT system and / or a first distributed artificial intelligence AI system; wherein,

[0006] The first DT system is configured to simulate a corresponding functional body, obtain measurement data, and report the measurement data to a second DT system in the operation and maintenance system, and provide data services to the first distributed AI system;

[0007] A first distributed AI system is configured to exchange information with a second distributed AI system in the operation and maintenance system, and execute the predetermined AI algorithm or predetermined task based on information obtained from the interaction. The first distributed AI system and the second distributed AI system are different parts of the distributed AI function, and the second distributed AI system and the first distributed AI system jointly execute the predetermined AI algorithm or predetermined task.

[0008] Furthermore, according to at least one embodiment of the present invention, the information exchanged between the first distributed AI system and the second distributed AI system includes at least one of the following information: the operating status of a preset AI algorithm, parameters calculated by the preset AI algorithm, and query, request, setting, or reporting information between different entities in the preset AI algorithm.

[0009] Furthermore, according to at least one embodiment of the present invention, the first distributed AI system is further configured to execute the distributed AI algorithm at a first time granularity; the first time granularity is smaller than a second time granularity, and the second time granularity is the time granularity at which the second distributed AI system executes the distributed AI algorithm;

[0010] or,

[0011] The first distributed AI system is further configured to execute a first part of a distributed AI algorithm, and the distributed AI algorithm further includes a second part executed by the second distributed AI system.

[0012] Furthermore, according to at least one embodiment of the present invention, the first DT system is an online DT system, which refers to a DT system that needs to run synchronously with the simulated functional body, and the measurement data includes at least one of the following data:

[0013] Online measurement data acquired and synchronously reported by the first DT system according to a third time granularity;

[0014] offline measurement data acquired by the first DT system according to a fourth time granularity and asynchronously reported,

[0015] Intermediate data generated by the first distributed AI system when executing a predetermined AI algorithm or a predetermined task;

[0016] Feature parameters of the managed object, where the feature parameters are used by the second DT system to generate a twin profile for the managed object;

[0017] Information used for operational maintenance of managed objects.

[0018] In addition, according to at least one embodiment of the present invention, the first distributed AI system is also used to receive the AI ​​model sent by the AI ​​model training system in the operation and maintenance system.

[0019] According to another aspect of the present invention, at least one embodiment provides an operation and maintenance system, comprising at least one application, and further comprising a second digital twin DT system and / or a second artificial intelligence AI system;

[0020] The second DT system is used to simulate the corresponding functional body, receive and store the measurement data reported by the first DT system of the managed object, and provide data services to the second AI system;

[0021] The second AI system is configured to receive measurement data provided by the second DT system and provide intelligent services to the application through an interface based on the measurement data provided by the second DT system; wherein,

[0022] The second AI system includes a second distributed AI system, which is the part of the distributed AI function running on the operation and maintenance system. The distributed AI function also includes a first distributed AI system running on the managed object. The second distributed AI system and the first distributed AI system jointly execute a predetermined AI algorithm or predetermined task.

[0023] Furthermore, according to at least one embodiment of the present invention, the second distributed AI system is further configured to exchange information with the first distributed AI system and execute the predetermined AI algorithm or predetermined task based on information obtained through the interaction, wherein the information obtained through the interaction includes at least one of the following information: the operating status of a preset AI algorithm, parameters calculated by the preset AI algorithm, and query, request, setting, or reporting information between different entities in the preset AI algorithm.

[0024] Furthermore, according to at least one embodiment of the present invention, the second distributed AI system is further configured to execute the distributed AI algorithm at a second time granularity; the second time granularity is greater than a first time granularity, the first time granularity being the time granularity at which the first distributed AI system executes the distributed AI algorithm;

[0025] or,

[0026] The second distributed AI system is further configured to execute a second part of a distributed AI algorithm, wherein the distributed AI algorithm also includes a first part executed by the first distributed AI system.

[0027] Furthermore, according to at least one embodiment of the present invention, the second DT system is an offline DT system, which refers to a DT system that does not need to run synchronously with the simulated functional body, and the measurement data includes at least one of the following data:

[0028] Online measurement data acquired and synchronously reported by the first DT system according to a third time granularity;

[0029] offline measurement data acquired by the first DT system according to a fourth time granularity and asynchronously reported,

[0030] Intermediate data generated by the first distributed AI system when executing a predetermined AI algorithm or a predetermined task;

[0031] Feature parameters of the managed object, where the feature parameters are used by the second DT system to generate a twin profile for the managed object;

[0032] Information used for operational maintenance of managed objects.

[0033] Furthermore, according to at least one embodiment of the present invention, the second AI system further includes an AI system for OAM;

[0034] The AI ​​system for OAM is used to perform OAM tasks of the operation and maintenance system itself.

[0035] Furthermore, according to at least one embodiment of the present invention, the second AI system further comprises an AI model training system;

[0036] The AI ​​model training system is used to train or update the AI ​​model and send the trained model or the updated AI model to the corresponding object, where the corresponding object includes: the AI ​​system for OAM, the second distributed AI system, and at least one of the managed objects.

[0037] According to another aspect of the present invention, at least one embodiment provides an operation and maintenance method for endogenous intelligence and digital twins, which is applied to a managed object, wherein the managed object includes a first digital twin DT system and / or a first distributed artificial intelligence (AI) system. The operation and maintenance method includes:

[0038] The managed object simulates the corresponding functional body through the first DT system, obtains measurement data, reports the measurement data to the second DT system in the operation and maintenance system, and provides data services to its own first distributed AI system;

[0039] The managed object exchanges information with the second distributed AI system in the operation and maintenance system through the first distributed AI system, and executes the predetermined AI algorithm or predetermined task based on the information obtained from the interaction. The first distributed AI system and the second distributed AI system are different parts of the distributed AI function, and the second distributed AI system and the first distributed AI system jointly execute the predetermined AI algorithm or predetermined task.

[0040] Furthermore, according to at least one embodiment of the present invention, the information exchanged between the first distributed AI system and the second distributed AI system includes at least one of the following information: the operating status of a preset AI algorithm, parameters calculated by the preset AI algorithm, and query, request, setting, or reporting information between different entities in the preset AI algorithm.

[0041] Furthermore, according to at least one embodiment of the present invention, the managed object further executes a distributed AI algorithm at a first time granularity through the first distributed AI system; the first time granularity is smaller than a second time granularity, and the second time granularity is the time granularity at which the second distributed AI system executes the distributed AI algorithm; or, executes a first part of a distributed AI algorithm, and the distributed AI algorithm also includes a second part executed by the second distributed AI system.

[0042] Furthermore, according to at least one embodiment of the present invention, the first DT system is an online DT system, which refers to a DT system that needs to run synchronously with the simulated functional body, and the measurement data includes at least one of the following data:

[0043] Online measurement data acquired and synchronously reported by the first DT system according to a third time granularity;

[0044] offline measurement data acquired by the first DT system according to a fourth time granularity and asynchronously reported,

[0045] Intermediate data generated by the first distributed AI system when executing a predetermined AI algorithm or a predetermined task;

[0046] Feature parameters of the managed object, where the feature parameters are used by the second DT system to generate a twin profile for the managed object;

[0047] Information used for operational maintenance of managed objects.

[0048] In addition, according to at least one embodiment of the present invention, the managed object also receives the AI ​​model sent by the AI ​​model training system in the operation and maintenance system through the first distributed AI system.

[0049] According to another aspect of the present invention, at least one embodiment provides an operation and maintenance method for endogenous intelligence and digital twins, which is applied to an operation and maintenance system. The operation and maintenance system includes at least one application and also includes a second digital twin DT system and / or a second artificial intelligence (AI) system. The operation and maintenance method includes:

[0050] The operation and maintenance system simulates the corresponding functional body through the second DT system, receives and stores the measurement data reported by the first DT system of the managed object, and provides data services to the second AI system;

[0051] The operation and maintenance system receives the measurement data provided by the second DT system through the second AI system, and provides intelligent services for the application through the interface based on the measurement data provided by the second DT system; wherein,

[0052] The second AI system includes a second distributed AI system, which is the part of the distributed AI function running on the operation and maintenance system. The distributed AI function also includes a first distributed AI system running on the managed object. The second distributed AI system and the first distributed AI system jointly execute a predetermined AI algorithm or predetermined task.

[0053] Furthermore, according to at least one embodiment of the present invention, the operation and maintenance system further exchanges information with the first distributed AI system through the second distributed AI system, and executes the predetermined AI algorithm or predetermined task based on information obtained through the interaction, wherein the information obtained through the interaction includes at least one of the following information: the operating status of the preset AI algorithm, parameters calculated by the preset AI algorithm, and query, request, setting, or reporting information between different entities in the preset AI algorithm.

[0054] Furthermore, according to at least one embodiment of the present invention, the operation and maintenance system further executes the distributed AI algorithm at a second time granularity through the second distributed AI system; the second time granularity is greater than the first time granularity, and the first time granularity is the time granularity at which the first distributed AI system executes the distributed AI algorithm; or, executes a second part of the distributed AI algorithm, where the distributed AI algorithm also includes the first part executed by the first distributed AI system.

[0055] Furthermore, according to at least one embodiment of the present invention, the second DT system is an offline DT system, which refers to a DT system that does not need to run synchronously with the simulated functional body, and the measurement data includes at least one of the following data:

[0056] Online measurement data acquired and synchronously reported by the first DT system according to a third time granularity;

[0057] offline measurement data acquired by the first DT system according to a fourth time granularity and asynchronously reported,

[0058] Intermediate data generated by the first distributed AI system when executing a predetermined AI algorithm or a predetermined task;

[0059] Feature parameters of the managed object, where the feature parameters are used by the second DT system to generate a twin profile for the managed object;

[0060] Information used for operational maintenance of managed objects.

[0061] Furthermore, according to at least one embodiment of the present invention, the second AI system further includes an AI system for OAM;

[0062] The operation and maintenance system also performs its own OAM tasks through the AI ​​system for OAM.

[0063] Furthermore, according to at least one embodiment of the present invention, the second AI system further comprises an AI model training system;

[0064] The operation and maintenance system also trains or updates the AI ​​model through the AI ​​model training system, and sends the trained model or the updated AI model to the corresponding object, where the corresponding object includes: the AI ​​system for OAM, the second distributed AI system, and at least one of the managed objects.

[0065] According to another aspect of the present invention, at least one embodiment provides a managed object, comprising: a processor, a memory, and a program stored in the memory and executable on the processor, wherein the program implements the steps of the method described above when executed by the processor.

[0066] According to another aspect of the present invention, at least one embodiment provides an operation and maintenance system, comprising: a processor, a memory, and a program stored in the memory and executable on the processor, wherein the program implements the steps of the above-described method when executed by the processor.

[0067] According to another aspect of the present invention, at least one embodiment provides a computer-readable storage medium having a program stored thereon. When the program is executed by a processor, the steps of the method described above are implemented.

[0068] Compared to existing technologies, the endogenous intelligence and digital twin operation and maintenance methods and devices provided by the present invention implement an OAM system for native AI, reducing the overhead of information reporting between the OAM system and managed objects. Furthermore, managed objects do not need to report original data, ensuring data security. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0070] Figure 1 A schematic diagram of a protocol stack for endogenous intelligence and digital twins in existing technologies;

[0071] Figure 2 Schematic diagram of the OAM functional model of endogenous intelligence and digital twins in an embodiment of the present invention;

[0072] Figure 3 A flowchart of interaction between the OAM system and the managed objects according to an embodiment of the present invention;

[0073] Figure 4 A flowchart of the operation and maintenance method of endogenous intelligence and digital twins provided in an embodiment of the present invention when applied to a managed object;

[0074] Figure 5 A flowchart of the operation and maintenance method of endogenous intelligence and digital twins provided in an embodiment of the present invention when applied to an OAM system;

[0075] Figure 6 An example diagram of OAM control of UE provided in an embodiment of the present invention;

[0076] Figure 7 A schematic diagram of the structure of a managed object provided by an embodiment of the present invention;

[0077] Figure 8 A schematic diagram of the structure of an OAM system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0078] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0079] The terms "first", "second" etc. in the specification and claims of the present application are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable in appropriate circumstances, so that the embodiments of the present application described herein, for example, can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprise" and "have" and any of their variations are intended to cover non-exclusive inclusions, for example, the process, method, system, product or equipment comprising a series of steps or units need not be limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or that are intrinsic to these processes, methods, products or equipment. "And / or" in the specification and claims represents at least one of the connected objects.

[0080] The following description provides examples and does not limit the scope, applicability, or configuration set forth in the claims. Changes may be made to the function and arrangement of the elements discussed without departing from the spirit and scope of this disclosure. The various examples may appropriately omit, substitute, or add various procedures or components. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. In addition, features described with reference to certain examples may be combined in other examples.

[0081] In 6G network research, endogenous intelligence and digital twins have become core features of 6G networks. 6G networks are considered to be networks with native AI. In 6G networks with native AI, AI no longer simply optimizes wireless resources; it becomes an integrated AI system that integrates the core network, transport network, and wireless access. 6G networks need to support services across multiple application scenarios, and only an intelligent 6G network can achieve these requirements.

[0082] The 6G Digital Twin (DT) system provides the fundamental operating environment for 6G's inherent intelligence. This provides the foundational support for AI-related processing and computing, while also simplifying the operational load and complexity of physical networks. In other words, the 6G Digital Twin system and the inherent intelligence system together comprise a series of online operations for physical network operations, including operation, maintenance, and application-oriented control computing. They become the brain of the physical network, directing every part of the network to deliver the services required by protocols or operators.

[0083] Figure 1A protocol stack solution of endogenous intelligence and digital twins in the prior art is provided. In the operation and maintenance system (OAM System), the AI ​​function (AI processing) is one of the functions of the DT system. Driven by the AI ​​function, the DT system generates various control or management operations. As described in the background technology, the AI ​​in the 4G / 5G network of the prior art is a plug-in AI. When running in the OAM system, there are problems such as high information reporting cost and the AI-generated strategy may be difficult to match the network needs. In order to solve at least one of the above problems, an embodiment of the present invention proposes an OAM function solution of endogenous intelligence and digital twins. In this solution, by defining the AI ​​and DT functions of the operation and maintenance system (OAM System), unified control and management of the network and terminals are achieved, and data security protection and a low-cost information solution on the interface are also achieved.

[0084] The embodiments of the present invention achieve data security and low-cost interface information reporting by defining unified distributed DT and distributed AI functions between the OAM system and managed objects (including but not limited to terminals, core networks, access networks, transmission networks, etc.).

[0085] Figure 2 The invention provides an OAM functional model of endogenous intelligence and digital twins, which includes an operation and maintenance system (OAM System) and a managed object (Managed Objective). In the embodiment of the invention, distributed AI refers to the fact that the AI ​​algorithms between different systems are logically different parts of a complete algorithm, or a logical constraint relationship maintained in order to complete a task. For example, the distributed AI algorithm on the OAM system is responsible for the operation of the first time granularity (large time granularity), and the distributed AI algorithms distributed to each functional body perform the corresponding operation of the second time granularity (small time granularity) under the unified management of the OAM system. The two have a coarse adjustment-fine adjustment logical relationship; for example, in order to ensure the security of measurement data, a complete AI algorithm is divided into two parts in the middle of the appropriate steps, one part of the algorithm is operated in the OAM system, and the other part is run on the functional body, so as to ensure that the data exchanged between the two is the data inside the algorithm, rather than the original plaintext data, so as to protect the security of the original data.

[0086] In this embodiment of the present invention, if a DT needs to run synchronously with the corresponding functional body, it is called an online DT; if a DT does not need to run synchronously with each corresponding function, it is called an offline DT. For online and offline DTs, offline and online are not related to traditional high / low real-time performance or fast / slow speed. Instead, offline and online reflect the synchronization relationship with the corresponding functional body. For example, an offline DT can obtain high-real-time data over a period of time through recording and broadcasting, and then process this data to obtain simulation results.

[0087] In this embodiment of the present invention, AI and DT between the operation and maintenance system (OAM system) and managed objects form a unified system. This system can be divided into two parts: distributed AI and offline DT, and distributed AI and online DT. DT within the OAM system is offline DT, while DT within managed objects is online DT.

[0088] The distributed AI and offline DT parts provide complete AI models, distributed AI models, large-time-scale control strategies, and managed object-level control strategies for the distributed AI and online DT parts.

[0089] The online AI and DT components perform online control and processing under the control of the offline AI and DT components. The information data reported by the online AI and DT components to the offline AI and DT components is calculated from the monitoring data generated during the online operation of the managed object system, not the original monitoring data.

[0090] like Figure 2 As shown, the managed objects include: the first DT system and / or the first distributed AI system. Optionally, the managed objects also include: various functional modules. The managed objects can specifically be terminals, access network devices, transmission network devices, core network devices, or their internal functions.

[0091] The operation and maintenance system (OAM System) includes: at least one application, and also includes a second DT system and / or a second AI system, and the second AI system includes a second distributed AI system. Optionally, the operation and maintenance system (OAM System) also includes: an AI system for operation and maintenance OAM (OAM AI Reference System), an AI model training system (Offline AI training system) and an open unified interface (Open interface to outside system). Here, the second AI system includes a second distributed AI system, which is the part of the distributed AI function running on the operation and maintenance system. The distributed AI function also includes a first distributed AI system running on the managed object, and the second distributed AI system and the first distributed AI system jointly execute a predetermined AI algorithm or predetermined task.

[0092] Specifically, among the managed objects:

[0093] The first DT system is configured to simulate a corresponding functional body, obtain measurement data, and report the measurement data to a second DT system in the operation and maintenance system, and provide data services to the first distributed AI system;

[0094] A first distributed AI system is configured to exchange information with a second distributed AI system in the operation and maintenance system, and execute the predetermined AI algorithm or predetermined task based on information obtained from the interaction. The first distributed AI system and the second distributed AI system are different parts of the distributed AI function, and the second distributed AI system and the first distributed AI system jointly execute the predetermined AI algorithm or predetermined task.

[0095] Here, the information exchanged between the first distributed AI system and the second distributed AI system includes at least one of the following information: the operating status of a preset AI algorithm, parameters calculated by the preset AI algorithm, and query, request, setting, or reporting information between different entities in the preset AI algorithm.

[0096] In an embodiment of the present invention, the first distributed AI system may also be configured to execute a distributed AI algorithm at a first time granularity; the first time granularity is smaller than a second time granularity, and the second time granularity is the time granularity at which the second distributed AI system executes the distributed AI algorithm; or, the first distributed AI system may be further configured to execute a first part of a distributed AI algorithm, and the distributed AI algorithm may also include a second part executed by the second distributed AI system.

[0097] Here, the first DT system is an online DT system, which refers to a DT system that needs to run synchronously with the simulated functional body, and the measurement data includes at least one of the following data:

[0098] Online measurement data acquired and synchronously reported by the first DT system according to a third time granularity;

[0099] offline measurement data acquired by the first DT system according to a fourth time granularity and asynchronously reported,

[0100] Intermediate data generated by the first distributed AI system when executing a predetermined AI algorithm or a predetermined task;

[0101] Feature parameters of the managed object, where the feature parameters are used by the second DT system to generate a twin profile for the managed object;

[0102] Information used for operational maintenance of managed objects.

[0103] In addition, the first distributed AI system is also used to receive the AI ​​model sent by the AI ​​model training system in the operation and maintenance system.

[0104] In the OAM system:

[0105] The second DT system is configured to simulate a corresponding functional body, receive and store measurement data reported by the first DT system of the managed object, and provide data services to the second AI system;

[0106] The second AI system is configured to receive measurement data provided by the second DT system, and provide intelligent services for the application through an interface based on the measurement data provided by the second DT system.

[0107] In addition, in an embodiment of the present invention, the second distributed AI system is further configured to interact with the first distributed AI system to execute the predetermined AI algorithm or predetermined task based on information obtained through interaction, wherein the information obtained through interaction includes at least one of the following information: the operating status of a preset AI algorithm, parameters calculated by the preset AI algorithm, and query, request, setting, or reporting information between different entities in the preset AI algorithm.

[0108] In this embodiment of the present invention, each online simulation function can have a corresponding distributed AI function, which has the capabilities of one or more AI algorithms. These distributed AI algorithms, under the control or management of the distributed AI algorithm of the OAM system, provide AI capability drivers for each online function. Here, AI capability drivers refer to the enhancement of related functions under the AI ​​algorithm, or the implementation of one or more online functions based on the AI ​​algorithm.

[0109] Optionally, the second distributed AI system is further used to execute the distributed AI algorithm at a second time granularity; the second time granularity is greater than the first time granularity, and the first time granularity is the time granularity at which the first distributed AI system executes the distributed AI algorithm; or, the second distributed AI system is further used to execute a second part of the distributed AI algorithm, and the distributed AI algorithm also includes the first part executed by the first distributed AI system.

[0110] As mentioned above, the second DT system may be an offline DT system. The offline DT system refers to a DT system that does not need to run synchronously with the simulated functional body. The measurement data includes at least one of the following data:

[0111] Online measurement data acquired and synchronously reported by the first DT system according to a third time granularity;

[0112] offline measurement data acquired by the first DT system according to a fourth time granularity and asynchronously reported,

[0113] Intermediate data generated by the first distributed AI system when executing a predetermined AI algorithm or a predetermined task;

[0114] Feature parameters of the managed object, where the feature parameters are used by the second DT system to generate a twin profile for the managed object;

[0115] Information used for operational maintenance of managed objects.

[0116] Optionally, the AI ​​system for OAM is used to perform OAM tasks of the operation and maintenance system itself. The AI ​​model training system is used to train or update the AI ​​model and send the trained or updated AI model to a corresponding object, wherein the corresponding object includes at least one of the AI ​​system for OAM, the second distributed AI system, and a managed object.

[0117] Figure 3 A schematic diagram of the interaction process between the OAM system and the managed objects is provided.

[0118] Steps 300 to 301 : Measurement Subscription & Measurement Report interaction between the second DT system (offline DT system) and the first DT system (online DT system).

[0119] Specifically, the second DT system (offline DT system) sends a measurement report subscription request message to the first DT system (online DT system), and the first DT system (online DT system) sends a measurement report to the second DT system (offline DT system) according to the request.

[0120] In this embodiment of the present invention, the second DT system (offline DT system) is responsible for processing, storing and sharing the measurement data of the OAM system, and provides the entire OAM system with the required data related to the managed objects. The data granularity stored in the offline DT system includes:

[0121] (a) Information data at a third time granularity, such as online measurement data reported by the managed object at a time granularity of 1 second (1s) (or greater than 1s) (online refers to measurement information that is synchronized with the operating state of the managed system of the managed object and is output to the offline DT system while the managed system is running);

[0122] (b) Information data at the fourth time granularity, such as offline measurement data reported by the managed object at 1ms (or less than 1s) or symbol level (offline means: these measurement information data are not measurement information synchronized with the management system operation, but system information measurement information with a small time granularity recorded by the management system and then reported to the offline DT system when system resources permit);

[0123] (c) Intermediate data generated by the distributed AI algorithm calculation process in the managed object. This type of data is the interaction data between the two distributed AI systems (Distributed AI in OAM and Distributed AI in MO). Different AI algorithms have different interactions; the same AI algorithm has different functional partitioning points and different interactions.

[0124] (d) The characteristic parameters of each managed object are used by the offline DT system to create a twin profile for each managed object;

[0125] (e) Information used for the operation and maintenance of the managed objects, including the initial configuration of the system startup, operating mode, abnormality monitoring, and other data information commonly used in the current 4G / 5G system.

[0126] Steps 302-303 interact with the DT system (including the offline DT system and the online DT system) and the AI ​​system (AI System for OAM, Distributed AI in OAM, Offline AI training system, and Distributed AI in Managed Objective). Subscription is the AI ​​system requesting data services from the DT system; reporting is the DT system providing data services to the AI ​​system. These data services can be periodic or one-time requests.

[0127] Step 304 reflects the interaction of AI within the distributed AI system (Distributed AI). The distributed AI in the OAM system and the AI ​​running on the managed object can be different parts of the same AI algorithm, or two independent algorithms with logical sequence or granularity constraints, or AI algorithm steps that assist each other. The information exchanged between the two distributed algorithms can be the status of the algorithm itself, parameter information that can be calculated by the algorithm, or other information queried, requested, set, or reported between different algorithm entities. The AI ​​operation status (Status Information exchange) parameter includes the interaction information between the two AI functional bodies.

[0128] Step 305 reflects the offline training function of the OAM system for the AI ​​algorithm. The OAM system provides the required AI model for the distributed AI function of the managed object through offline training of the AI ​​model, including configuration and update of the AI ​​model.

[0129] In the embodiment of the present invention, the offline DT system in the operation and maintenance system (OAM System) is responsible for data storage, processing and offline simulation functions, and provides data support for the AI ​​system; the AI ​​system provides intelligent services to various applications through interfaces. These applications can be services related to the local network or third-party applications. The online DT system (Online DT System) in the managed object provides the required online data information and online simulation functions to the distributed AI system (Distributed AI System), and the distributed AI system provides intelligent services to various functions (Functions) of the managed end objects.

[0130] Based on the above functional model, an embodiment of the present invention provides an operation and maintenance method of endogenous intelligence and digital twins, which is applied to the managed objects mentioned above, wherein the managed objects include a first digital twin DT system and / or a first distributed artificial intelligence AI system, such as Figure 4 As shown, the operation and maintenance method includes:

[0131] Step 41: The managed object simulates the corresponding functional body through the first DT system, obtains measurement data, reports the measurement data to the second DT system in the operation and maintenance system, and provides data services to its own first distributed AI system.

[0132] In step 42, the managed object exchanges information with the second distributed AI system in the operation and maintenance system through the first distributed AI system, and executes the predetermined AI algorithm or predetermined task based on the information obtained from the interaction. The first distributed AI system and the second distributed AI system are different parts of the distributed AI function, and the second distributed AI system and the first distributed AI system jointly execute the predetermined AI algorithm or predetermined task.

[0133] Through the above steps, the embodiment of the present invention realizes an operation and maintenance system for endogenous AI, and can reduce the overhead of information reporting between the operation and maintenance system and the managed objects.

[0134] Optionally, the information exchanged between the first distributed AI system and the second distributed AI system includes at least one of the following information: the operating status of a preset AI algorithm, parameters calculated by the preset AI algorithm, and query, request, setting, or reporting information between different entities in the preset AI algorithm.

[0135] Optionally, the managed object further executes a distributed AI algorithm at a first time granularity through the first distributed AI system; the first time granularity is smaller than a second time granularity, and the second time granularity is the time granularity at which the second distributed AI system executes the distributed AI algorithm; or, executes a first part of a distributed AI algorithm, and the distributed AI algorithm also includes a second part executed by the second distributed AI system.

[0136] Optionally, the first DT system is an online DT system, which refers to a DT system that needs to run synchronously with the simulated functional body, and the measurement data includes at least one of the following data:

[0137] Online measurement data acquired and synchronously reported by the first DT system according to a third time granularity;

[0138] offline measurement data acquired by the first DT system according to a fourth time granularity and asynchronously reported,

[0139] Intermediate data generated by the first distributed AI system when executing a predetermined AI algorithm or a predetermined task;

[0140] Feature parameters of the managed object, where the feature parameters are used by the second DT system to generate a twin profile for the managed object;

[0141] Information used for operational maintenance of managed objects.

[0142] Optionally, the managed object also receives the AI ​​model sent by the AI ​​model training system in the operation and maintenance system through the first distributed AI system.

[0143] Please refer to Figure 5 The embodiment of the present invention also provides an operation and maintenance method of endogenous intelligence and digital twins, which is applied to the operation and maintenance system described above. The operation and maintenance system includes at least one application and also includes a second digital twin DT system and / or a second artificial intelligence AI system, such as Figure 5 As shown, the operation and maintenance method includes:

[0144] Step 51: The operation and maintenance system simulates the corresponding functional body through the second DT system, receives and stores the measurement data reported by the first DT system of the managed object, and provides data services to the second AI system;

[0145] In step 52 , the operation and maintenance system receives the measurement data provided by the second DT system through the second AI system, and provides intelligent services for the application through an interface based on the measurement data provided by the second DT system.

[0146] Here, the second AI system includes a second distributed AI system, which is the part of the distributed AI function running on the operation and maintenance system. The distributed AI function also includes a first distributed AI system running on the managed object. The second distributed AI system and the first distributed AI system jointly execute a predetermined AI algorithm or predetermined task.

[0147] Optionally, the operation and maintenance system further exchanges information with the first distributed AI system through the second distributed AI system, and executes the predetermined AI algorithm or predetermined task based on information obtained through the interaction, wherein the information obtained through the interaction includes at least one of the following information: the operating status of the preset AI algorithm, parameters calculated by the preset AI algorithm, and query, request, setting, or reporting information between different entities in the preset AI algorithm.

[0148] Optionally, the operation and maintenance system further executes the distributed AI algorithm at a second time granularity through the second distributed AI system; the second time granularity is greater than the first time granularity, and the first time granularity is the time granularity at which the first distributed AI system executes the distributed AI algorithm; or, executes the second part of the distributed AI algorithm, and the distributed AI algorithm also includes the first part executed by the first distributed AI system.

[0149] Optionally, the second DT system is an offline DT system, which refers to a DT system that does not need to run synchronously with the simulated functional body, and the measurement data includes at least one of the following data:

[0150] Online measurement data acquired and synchronously reported by the first DT system according to a third time granularity;

[0151] offline measurement data acquired by the first DT system according to a fourth time granularity and asynchronously reported,

[0152] Intermediate data generated by the first distributed AI system when executing a predetermined AI algorithm or a predetermined task;

[0153] Feature parameters of the managed object, where the feature parameters are used by the second DT system to generate a twin profile for the managed object;

[0154] Information used for operational maintenance of managed objects.

[0155] Optionally, the second AI system further includes an AI system for OAM;

[0156] The operation and maintenance system also performs its own OAM tasks through the AI ​​system for OAM.

[0157] Optionally, the second AI system further includes an AI model training system;

[0158] The operation and maintenance system also trains or updates the AI ​​model through the AI ​​model training system, and sends the trained model or the updated AI model to the corresponding object, where the corresponding object includes: the AI ​​system for OAM, the second distributed AI system, and at least one of the managed objects.

[0159] The above method is further described below by taking an example of the control process of OAM on UE (managed object).

[0160] Figure 6 An example of OAM control over UE is provided, in which:

[0161] On the OAM side:

[0162] OAM offline DT includes:

[0163] Measurement Processing: This module collects, categorizes, cleans, and aggregates measurement data. Measurement data primarily includes information about UE data transmission on the network side (cache changes, transmission success / failure statistics, QoS configuration requirements, and data transmission status for bearer, logical channel, and transport channel statistics).

[0164] Information Storing functional module: This module stores measurement data and provides a unified access interface.

[0165] Digital Twin of Network Element: The digital twin of each network element of this module, such as the functional core network, transmission network, and base station.

[0166] Digital Twin of UE: This module’s functionality is for the digital twin of the UE, including the UE’s software, hardware, communication capabilities, and other characteristic values.

[0167] OAM's AI capabilities include:

[0168] OAM internal AI-driven functions: These correspond to the O&M AI Reference System functions and are used to intelligently operate OAM itself.

[0169] AI-driven management and control: This corresponds to the Distributed AI Reference System and controls the UE's AI, coordinating the operation and coordination of AI algorithms on the network and the terminal. This includes interacting with measurement information and defining the functions performed by each AI.

[0170] Offline AI Training System: This system trains AI models based on the DT system, providing AI models for internal AI-driven functions and AI-driven management and control.

[0171] Based on the AI ​​layer, control is provided for the UE's non-access stratum (NAS), access stratum (AS), DT layer and AI layer.

[0172] As can be seen from the above, in the endogenous intelligence and digital twin OAM functional solutions provided by the embodiments of the present invention, the DT system is divided into an offline DT system and an online DT system. The AI ​​system is divided into the AI ​​system for OAM, the distributed AI system, and AI model training. The DT system is responsible for data processing and offline / online simulation functions of the AI ​​system. The OAM system is the unified management system for the entire DT and AI system, managing the DT and AI in the managed objects through offline, online, and distributed methods. Furthermore, within the OAM system and managed objects, the DT system supports the AI ​​system, and the AI ​​system provides services to applications.

[0173] This embodiment of the present invention implements an OAM system for native AI, reducing the overhead of information reporting between the OAM system and managed objects. Furthermore, managed objects do not need to report raw data, ensuring data security. Within the native AI system, AI can be divided into different components for operation. The DT system and AI system form a fused system, complementing each other.

[0174] Please refer to Figure 7 , a structural diagram of a terminal provided by an embodiment of the present invention, the terminal includes: a processor 701, a transceiver 702, a memory 703, a user interface and a bus interface.

[0175] In the embodiment of the present invention, the terminal further includes: a program stored in the memory 703 and executable on the processor 701 .

[0176] When the processor 701 executes the program, the following steps are implemented:

[0177] Through the first DT system, the corresponding functional body is simulated to obtain measurement data and report the measurement data to the second DT system in the operation and maintenance system, and data services are provided to the first distributed AI system thereof;

[0178] Information is exchanged with a second distributed AI system in the operation and maintenance system through the first distributed AI system, and the predetermined AI algorithm or predetermined task is executed based on the information obtained from the interaction. The first distributed AI system and the second distributed AI system are different parts of the distributed AI function, and the second distributed AI system and the first distributed AI system jointly execute the predetermined AI algorithm or predetermined task.

[0179] Optionally, the information exchanged between the first distributed AI system and the second distributed AI system includes at least one of the following information: the operating status of a preset AI algorithm, parameters calculated by the preset AI algorithm, and query, request, setting, or reporting information between different entities in the preset AI algorithm.

[0180] Optionally, when executing the program, the processor further implements the following steps:

[0181] The distributed AI algorithm is executed at a first time granularity by the first distributed AI system; the first time granularity is smaller than a second time granularity, and the second time granularity is the time granularity at which the second distributed AI system executes the distributed AI algorithm; or a first portion of the distributed AI algorithm is executed, and the distributed AI algorithm also includes a second portion executed by the second distributed AI system.

[0182] Optionally, the first DT system is an online DT system, which refers to a DT system that needs to run synchronously with the simulated functional body, and the measurement data includes at least one of the following data:

[0183] Online measurement data acquired and synchronously reported by the first DT system according to a third time granularity;

[0184] offline measurement data acquired by the first DT system according to a fourth time granularity and asynchronously reported,

[0185] Intermediate data generated by the first distributed AI system when executing a predetermined AI algorithm or a predetermined task;

[0186] Feature parameters of the managed object, where the feature parameters are used by the second DT system to generate a twin profile for the managed object;

[0187] Information used for operational maintenance of managed objects.

[0188] Optionally, when executing the program, the processor further implements the following steps:

[0189] The AI ​​model sent by the AI ​​model training system in the operation and maintenance system is received through the first distributed AI system.

[0190] exist Figure 7In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically linking together various circuits of one or more processors represented by processor 701 and memory represented by memory 703. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. The transceiver 702 may be a plurality of components, i.e., a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium. For different user devices, the user interface may also be an interface capable of connecting external or internal devices as required, and the connected devices include but are not limited to a keypad, a display, a speaker, a microphone, a joystick, etc.

[0191] The processor 701 is responsible for managing the bus architecture and general processing, and the memory 703 can store data used by the processor 701 when performing operations.

[0192] It should be noted that the device in this embodiment is the same as the above Figure 4 The device corresponding to the method shown is applicable to the implementation methods in the above embodiments and can achieve the same technical effects. In the device, the transceiver 702 and the memory 703, as well as the transceiver 702 and the processor 701, can be communicatively connected via a bus interface. The functions of the processor 701 can also be implemented by the transceiver 702, and the functions of the transceiver 702 can also be implemented by the processor 701. It should be noted that the above device provided by the embodiment of the present invention can implement all the method steps implemented in the above method embodiment and can achieve the same technical effects. The parts and beneficial effects of this embodiment that are the same as those in the method embodiment will not be detailed here.

[0193] In some embodiments of the present invention, a computer-readable storage medium is further provided, on which a program is stored. When the program is executed by a processor, the following steps are implemented:

[0194] Through the first DT system, the corresponding functional body is simulated to obtain measurement data and report the measurement data to the second DT system in the operation and maintenance system, and data services are provided to the first distributed AI system thereof;

[0195] Information is exchanged with a second distributed AI system in the operation and maintenance system through the first distributed AI system, and the predetermined AI algorithm or predetermined task is executed based on the information obtained from the interaction. The first distributed AI system and the second distributed AI system are different parts of the distributed AI function, and the second distributed AI system and the first distributed AI system jointly execute the predetermined AI algorithm or predetermined task.

[0196] When the program is executed by the processor, it can implement all the implementation methods of the above-mentioned operation and maintenance methods of the intrinsic intelligence and digital twins applied to the managed objects, and can achieve the same technical effects. To avoid repetition, it will not be repeated here.

[0197] Please refer to Figure 8 , an embodiment of the present invention provides a schematic diagram of a structure of a network side device, including: a processor 801, a transceiver 802, a memory 803 and a bus interface, wherein:

[0198] In the embodiment of the present invention, the network-side device further includes: a program stored in the memory 803 and executable on the processor 801, wherein the program, when executed by the processor 801, implements the following steps:

[0199] Through the second DT system, the corresponding functional body is simulated to receive and store the measurement data reported by the first DT system of the managed object, and provide data services to the second AI system;

[0200] The second AI system receives the measurement data provided by the second DT system, and provides intelligent services for the application through the interface based on the measurement data provided by the second DT system; wherein,

[0201] The second AI system includes a second distributed AI system, which is the part of the distributed AI function running on the operation and maintenance system. The distributed AI function also includes a first distributed AI system running on the managed object. The second distributed AI system and the first distributed AI system jointly execute a predetermined AI algorithm or predetermined task.

[0202] Optionally, when executing the program, the processor further implements the following steps:

[0203] Information is exchanged with the first distributed AI system through the second distributed AI system, and the predetermined AI algorithm or predetermined task is executed based on information obtained from the interaction, where the information obtained from the interaction includes at least one of the following information: an operating status of a preset AI algorithm, parameters calculated by the preset AI algorithm, and query, request, setting, or report information between different entities in the preset AI algorithm.

[0204] Optionally, when executing the program, the processor further implements the following steps:

[0205] Executing, by the second distributed AI system, a distributed AI algorithm at a second time granularity; the second time granularity is greater than the first time granularity, the first time granularity being the time granularity at which the first distributed AI system executes the distributed AI algorithm; or executing a second portion of the distributed AI algorithm, the distributed AI algorithm also including the first portion executed by the first distributed AI system.

[0206] Optionally, the second DT system is an offline DT system, which refers to a DT system that does not need to run synchronously with the simulated functional body, and the measurement data includes at least one of the following data:

[0207] Online measurement data acquired and synchronously reported by the first DT system according to a third time granularity;

[0208] offline measurement data acquired by the first DT system according to a fourth time granularity and asynchronously reported,

[0209] Intermediate data generated by the first distributed AI system when executing a predetermined AI algorithm or a predetermined task;

[0210] Feature parameters of the managed object, where the feature parameters are used by the second DT system to generate a twin profile for the managed object;

[0211] Optionally, the second AI system further includes an AI system for OAM;

[0212] Optionally, when executing the program, the processor further implements the following steps:

[0213] The OAM tasks of the operation and maintenance system itself are performed by the AI ​​system for OAM.

[0214] Optionally, the second AI system further includes an AI model training system; when the processor executes the program, the processor further implements the following steps:

[0215] The AI ​​model training system is used to train or update the AI ​​model, and the trained model or the updated AI model is sent to a corresponding object, where the corresponding object includes at least one of the AI ​​system for OAM, the second distributed AI system, and the managed object.

[0216] exist Figure 8In the embodiment of the present invention, the bus architecture can include any number of interconnected buses and bridges, specifically linking various circuits such as one or more processors represented by processor 801 and memory represented by memory 803. The bus architecture can also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore not further described herein. The bus interface provides an interface. The transceiver 802 can be multiple components, namely, a transmitter and a receiver, providing a means for communicating with various other devices over a transmission medium.

[0217] The processor 801 is responsible for managing the bus architecture and general processing, and the memory 803 can store data used by the processor 801 when performing operations.

[0218] It should be noted that the terminal in this embodiment is the same as the above Figure 5 The device corresponding to the method shown, and the implementation methods in the above embodiments are all applicable to the embodiments of the terminal, and can also achieve the same technical effects. In this device, transceiver 802 and memory 803, as well as transceiver 802 and processor 801, can be communicatively connected via a bus interface. The functions of processor 801 can also be implemented by transceiver 802, and the functions of transceiver 802 can also be implemented by processor 801. It should be noted that the above-mentioned device provided by the embodiment of the present invention can implement all the method steps implemented by the above-mentioned method embodiment and can achieve the same technical effects. The parts and beneficial effects of this embodiment that are the same as those of the method embodiment will not be detailed here.

[0219] In some embodiments of the present invention, a computer-readable storage medium is further provided, on which a program is stored. When the program is executed by a processor, the following steps are implemented:

[0220] Through the second DT system, the corresponding functional body is simulated to receive and store the measurement data reported by the first DT system of the managed object, and provide data services to the second AI system;

[0221] The second AI system receives the measurement data provided by the second DT system, and provides intelligent services for the application through the interface based on the measurement data provided by the second DT system; wherein,

[0222] The second AI system includes a second distributed AI system, which is the part of the distributed AI function running on the operation and maintenance system. The distributed AI function also includes a first distributed AI system running on the managed object. The second distributed AI system and the first distributed AI system jointly execute a predetermined AI algorithm or predetermined task.

[0223] When the program is executed by the processor, it can implement all the implementation methods of the above-mentioned operation and maintenance methods of the endogenous wisdom and digital twin applied to the OAM system, and can achieve the same technical effects. To avoid repetition, it will not be repeated here.

[0224] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0225] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0226] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0227] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the objectives of the embodiments of the present invention.

[0228] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0229] If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or the portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard drive, ROM, RAM, a magnetic disk, or an optical disk.

[0230] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A managed device, characterized in that: Including the first digital twin DT system and the first distributed artificial intelligence AI system; among them, The first DT system is configured to simulate a corresponding functional body, obtain measurement data, and report the measurement data to a second DT system in the operation and maintenance system, and provide data services to the first distributed AI system; A first distributed AI system is configured to exchange information with a second distributed AI system in the operation and maintenance system, and execute a predetermined AI algorithm or predetermined task based on information obtained from the interaction. The first distributed AI system and the second distributed AI system are different parts of a distributed AI function, and the second distributed AI system and the first distributed AI system jointly execute the predetermined AI algorithm or predetermined task.

2. The managed device according to claim 1, wherein: The information exchanged between the first distributed AI system and the second distributed AI system includes at least one of the following information: the operating status of a preset AI algorithm, parameters calculated by the preset AI algorithm, and query, request, setting, or reporting information between different entities in the preset AI algorithm.

3. The managed device according to claim 1, wherein: The first distributed AI system is further configured to execute the distributed AI algorithm at a first time granularity; the first time granularity is smaller than a second time granularity, and the second time granularity is the time granularity at which the second distributed AI system executes the distributed AI algorithm; or, The first distributed AI system is further configured to execute a first part of a distributed AI algorithm, and the distributed AI algorithm further includes a second part executed by the second distributed AI system.

4. The managed device according to claim 1, wherein: The first DT system is an online DT system, which refers to a DT system that needs to run synchronously with the simulated functional body. The measurement data includes at least one of the following data: Online measurement data acquired and synchronously reported by the first DT system according to a third time granularity; offline measurement data acquired by the first DT system according to a fourth time granularity and asynchronously reported, Intermediate data generated by the first distributed AI system when executing a predetermined AI algorithm or a predetermined task; Characteristic parameters of the managed device, which are used by the second DT system to generate a twin profile for the managed device; Information used for operational maintenance of managed devices.

5. The managed device according to any one of claims 1 to 4, characterized in that: The first distributed AI system is also used to receive the AI ​​model sent by the AI ​​model training system in the operation and maintenance system.

6. An operation and maintenance system, characterized in that: The system includes at least one application, a second digital twin DT system, and a second artificial intelligence AI system; The second DT system is used to simulate the corresponding functional body, receive and store the measurement data reported by the first DT system of the managed object, and provide data services to the second AI system; The second AI system is configured to receive measurement data provided by the second DT system and provide intelligent services to the application through an interface based on the measurement data provided by the second DT system; wherein, The second AI system includes a second distributed AI system, which is the part of the distributed AI function running on the operation and maintenance system. The distributed AI function also includes a first distributed AI system running on the managed object. The second distributed AI system and the first distributed AI system jointly execute a predetermined AI algorithm or predetermined task.

7. The operation and maintenance system according to claim 6, wherein: The second distributed AI system is further configured to exchange information with the first distributed AI system and execute the predetermined AI algorithm or predetermined task based on information obtained through the interaction, wherein the information obtained through the interaction includes at least one of the following: an operating status of a preset AI algorithm, parameters calculated by the preset AI algorithm, and query, request, setting, or reporting information between different entities in the preset AI algorithm.

8. The operation and maintenance system according to claim 6, wherein: The second distributed AI system is further configured to execute the distributed AI algorithm at a second time granularity; the second time granularity is greater than the first time granularity, the first time granularity being the time granularity at which the first distributed AI system executes the distributed AI algorithm; or, The second distributed AI system is further configured to execute a second part of a distributed AI algorithm, wherein the distributed AI algorithm also includes a first part executed by the first distributed AI system.

9. The operation and maintenance system according to claim 6, wherein: The second DT system is an offline DT system, which refers to a DT system that does not need to run synchronously with the simulated functional body, and the measurement data includes at least one of the following data: Online measurement data acquired and synchronously reported by the first DT system according to a third time granularity; offline measurement data acquired by the first DT system according to a fourth time granularity and asynchronously reported, Intermediate data generated by the first distributed AI system when executing a predetermined AI algorithm or a predetermined task; Feature parameters of the managed object, where the feature parameters are used by the second DT system to generate a twin profile for the managed object; Information used for operational maintenance of managed objects.

10. The operation and maintenance system according to any one of claims 6 to 9, characterized in that: The second AI system also includes an AI system for OAM; The AI ​​system for OAM is used to perform OAM tasks of the operation and maintenance system itself.

11. The operation and maintenance system according to claim 10, wherein: The second AI system also includes an AI model training system; The AI ​​model training system is used to train or update the AI ​​model and send the trained model or the updated AI model to the corresponding object, where the corresponding object includes: the AI ​​system for OAM, the second distributed AI system, and at least one of the managed objects.

12. An operation and maintenance method of endogenous intelligence and digital twins, applied to a managed object, characterized in that: The managed objects include a first digital twin DT system and a first distributed artificial intelligence AI system, and the operation and maintenance method includes: The managed object simulates the corresponding functional body through the first DT system, obtains measurement data, reports the measurement data to the second DT system in the operation and maintenance system, and provides data services to its own first distributed AI system; The managed object exchanges information with a second distributed AI system in the operation and maintenance system through the first distributed AI system, and executes a predetermined AI algorithm or predetermined task based on the information obtained from the interaction. The first distributed AI system and the second distributed AI system are different parts of the distributed AI function, and the second distributed AI system and the first distributed AI system jointly execute the predetermined AI algorithm or predetermined task.

13. The operation and maintenance method according to claim 12, wherein: The information exchanged between the first distributed AI system and the second distributed AI system includes at least one of the following information: the operating status of a preset AI algorithm, parameters calculated by the preset AI algorithm, and query, request, setting, or reporting information between different entities in the preset AI algorithm.

14. The operation and maintenance method according to claim 12, wherein: The managed object further executes a distributed AI algorithm at a first time granularity through the first distributed AI system; the first time granularity is smaller than a second time granularity, and the second time granularity is the time granularity at which the second distributed AI system executes the distributed AI algorithm; or, executes a first part of a distributed AI algorithm, and the distributed AI algorithm also includes a second part executed by the second distributed AI system.

15. The operation and maintenance method according to claim 12, wherein: The first DT system is an online DT system, which refers to a DT system that needs to run synchronously with the simulated functional body. The measurement data includes at least one of the following data: Online measurement data acquired and synchronously reported by the first DT system according to a third time granularity; offline measurement data acquired by the first DT system according to a fourth time granularity and asynchronously reported, Intermediate data generated by the first distributed AI system when executing a predetermined AI algorithm or a predetermined task; Feature parameters of the managed object, where the feature parameters are used by the second DT system to generate a twin profile for the managed object; Information used for operational maintenance of managed objects.

16. The operation and maintenance method according to any one of claims 12 to 15, characterized in that: The managed object also receives the AI ​​model sent by the AI ​​model training system in the operation and maintenance system through the first distributed AI system.

17. An operation and maintenance method based on endogenous intelligence and digital twins, applied to an operation and maintenance system, characterized in that: The operation and maintenance system includes at least one application, a second digital twin DT system, and a second artificial intelligence AI system. The operation and maintenance method includes: The operation and maintenance system simulates the corresponding functional body through the second DT system, receives and stores the measurement data reported by the first DT system of the managed object, and provides data services to the second AI system; The operation and maintenance system receives the measurement data provided by the second DT system through the second AI system, and provides intelligent services for the application through the interface based on the measurement data provided by the second DT system; wherein, The second AI system includes a second distributed AI system, which is the part of the distributed AI function running on the operation and maintenance system. The distributed AI function also includes a first distributed AI system running on the managed object. The second distributed AI system and the first distributed AI system jointly execute a predetermined AI algorithm or predetermined task.

18. The operation and maintenance method according to claim 17, wherein: The operation and maintenance system also exchanges information with the first distributed AI system through the second distributed AI system, and executes the predetermined AI algorithm or predetermined task based on information obtained from the interaction, wherein the information obtained from the interaction includes at least one of the following information: the operating status of the preset AI algorithm, parameters calculated by the preset AI algorithm, and query, request, setting, or report information between different entities in the preset AI algorithm.

19. The operation and maintenance method according to claim 17, wherein: The operation and maintenance system further executes the distributed AI algorithm at a second time granularity through the second distributed AI system; the second time granularity is greater than the first time granularity, and the first time granularity is the time granularity at which the first distributed AI system executes the distributed AI algorithm; Alternatively, a second part of a distributed AI algorithm is executed, wherein the distributed AI algorithm also includes a first part executed by the first distributed AI system.

20. The operation and maintenance method according to claim 17, wherein: The second DT system is an offline DT system, which refers to a DT system that does not need to run synchronously with the simulated functional body, and the measurement data includes at least one of the following data: Online measurement data acquired and synchronously reported by the first DT system according to a third time granularity; offline measurement data acquired by the first DT system according to a fourth time granularity and asynchronously reported, Intermediate data generated by the first distributed AI system when executing a predetermined AI algorithm or a predetermined task; Feature parameters of the managed object, where the feature parameters are used by the second DT system to generate a twin profile for the managed object; Information used for operational maintenance of managed objects.

21. The operation and maintenance method according to any one of claims 17 to 20, characterized in that: The second AI system also includes an AI system for OAM; The operation and maintenance system also performs its own OAM tasks through the AI ​​system for OAM.

22. The operation and maintenance method according to claim 21, wherein: The second AI system also includes an AI model training system; The operation and maintenance system also trains or updates the AI ​​model through the AI ​​model training system, and sends the trained model or the updated AI model to the corresponding object, where the corresponding object includes: the AI ​​system for OAM, the second distributed AI system, and at least one of the managed objects.

23. A managed device, characterized in that: include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the steps of the method according to any one of claims 12 to 16 are implemented.

24. An operation and maintenance system, characterized in that: include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the steps of the method according to any one of claims 17 to 22 are implemented.

25. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 12 to 22.

Images