Method and equipment for realizing endogenous intelligence and digital twins in non-access layer

Abstract

A method and device for implementing endogenous intelligence and digital twins of a non-access layer, wherein the method includes: the first AIF of the terminal provides an AI capability driver for the first DTF under the control or management of a third distributed AI system in an operation and maintenance system; the first DTF of the terminal synchronously obtains relevant information of a first NAS functional body, and utilizes the AI ​​capability driver provided by the first distributed AIF to simulate the function of the first NAS functional body online, and obtains first measurement data and reports the first measurement data to a second DTF in a core network, wherein the first measurement data includes at least one of the following information: relevant information of the first NAS functional body, the operating status of the first AIF, the operating status of the first DTF, and the supporting data required for the AI ​​operation on the network side. The embodiment of the present invention implements a non-access layer with endogenous intelligence and digital twin functions, and can reduce the overhead of information reporting between the operation and maintenance system and the managed object.

Description

Technical Field

[0001] The present invention relates to the field of mobile communication technology, and in particular to a method and device for realizing endogenous intelligence of a non-access stratum (NAS). Background Art

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

[0003] Currently, AI in 4G / 5G networks is plug-in AI and runs in the operations and maintenance (OAM) system. There are two insurmountable challenges: 1) In order to make the AI ​​operation results more accurate or more effective, a large amount of real-time and fine-grained measurement information needs to be reported to the OAM system. The cost and interoperability (interconnection of abnormal parts) of this method are difficult to commercialize in commercial networks; 2) Due to the limitations of the transmission network itself connected to the OAM side, the effectiveness of AI on the network depends on the accuracy of the measurement data, resulting in the results of AI operation or the generated strategies may not match the needs of the network, making it difficult to reflect the gains brought by AI to the network, and thus difficult to realize the vision of a smart network. Summary of the invention

[0004] At least one embodiment of the present invention provides a method and device for realizing the intrinsic intelligence and digital twin of a non-access layer, realizing a non-access layer with intrinsic intelligence and digital twin functions, and capable of reducing the overhead of information reporting between an operation and maintenance system and a managed object.

[0005] According to one aspect of the present invention, at least one embodiment provides a terminal, wherein a non-access layer NAS of the terminal includes a first digital twin function DTF and / or a first artificial intelligence function AIF; wherein,

[0006] A first AIF, configured to provide an AI capability driver for the first DTF under the control or management of a third distributed AI system in the operation and maintenance system;

[0007] The first DTF is used to synchronously obtain relevant information of the first NAS function body, and use the AI ​​capability provided by the first distributed AIF to drive the online simulation of the function of the first NAS function body, and obtain first measurement data and report the first measurement data to the second DTF in the core network, where the first measurement data includes at least one of the following information: relevant information of the first NAS function body, the operating status of the first AIF, the operating status of the first DTF, and supporting data required for AI operation on the network side.

[0008] In addition, according to at least one embodiment of the present invention, the first DTF is further used to perform at least one of the following functions when simulating the function of the corresponding first NAS function body: predicting the state of the corresponding first NAS function body, decomposing the computational load of the corresponding first NAS function body, pre-executing control signaling to minimize the end-to-end control cost and select a control signaling scheme, and selecting an optimal logical path for collaboration between the first NAS functions of the terminal.

[0009] In addition, according to at least one embodiment of the present invention, the first DTF includes at least one first DT system, each of which simulates a first NAS function body;

[0010] The first AIF includes a first distributed AI system corresponding to each of the first DT systems, wherein the first distributed AI system, the second distributed AI system and the third distributed AI system are different parts of the distributed AI function, which jointly execute a predetermined AI algorithm or a predetermined task, and the second distributed AI system is a distributed AI system arranged in the core network.

[0011] In addition, according to at least one embodiment of the present invention, the first DT system is used to perform online simulation of the corresponding first NAS functional body under the unified control or management of the third DT system in the operation and maintenance system, and the third 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;

[0012] The first distributed AI system is used to operate under the unified control of the third distributed AI system in the operation and maintenance system, and to execute the predetermined AI algorithm or predetermined task based on information obtained from the interaction by interacting with the second distributed AI system and / or the third distributed AI system.

[0013] In addition, according to at least one embodiment of the present invention, the first DT system synchronizes information with the corresponding first NAS functional body by sharing data cache or operation information cache, or by data and information sharing.

[0014] In addition, according to at least one embodiment of the present invention, the first DT system is further used to receive the first information and / or the second information, and based on the first information and / or the second information, online simulate the operation of the corresponding first NAS function body, and under the drive of the AI ​​algorithm provided by the first distributed AI system, generate signaling, policies and commands for the first NAS function body and send them to the corresponding first NAS function body for processing; wherein the first information is the input information of the corresponding first NAS function body, and the second information is the information generated during the operation of the corresponding first NAS function body.

[0015] In addition, according to at least one embodiment of the present invention, the first DTF further includes a first controller and a third distributed AI system, wherein:

[0016] The first controller is used to control and arrange the functions of each first DT system under the drive of the third distributed AI system.

[0017] Furthermore, according to at least one embodiment of the present invention, the third distributed AI system is used to select at least one alternative optimization solution and provide it to the controller based on the input information and the characteristics of each first DT system;

[0018] The first controller is also used to select one or more candidate optimization schemes from the alternative optimization schemes, and configure them to the corresponding first DT system for operation, and select a final optimization scheme based on the operation results of the candidate optimizations, and send configuration information to the relevant first NAS function body through signaling, policy or command based on the final optimization scheme.

[0019] In addition, according to at least one embodiment of the present invention, the first DTF further includes a first data or information sharing function and a fourth distributed AI system;

[0020] The fourth distributed AI system is used to use an AI algorithm to optimize the information stored in the first data or information sharing functional body, and record the data or information obtained after the optimization iteration to provide it to each first DT system for use.

[0021] According to another aspect of the present invention, at least one embodiment provides a core network, wherein the core network includes a second DTF and / or a second AIF; wherein:

[0022] A second AIF is used to provide an AI capability driver for the second DTF under the control or management of a third distributed AI system in the operation and maintenance system;

[0023] The second DTF is used to synchronously obtain relevant information of the second NAS function body and receive the first measurement data reported by the terminal; use the AI ​​capability provided by the second distributed AIF to drive, based on the relevant information of the second NAS function body and the first measurement data, online simulate the function of the second NAS function body; and obtain the second measurement data and report the second measurement data to the third DTF in the OAM, where the second measurement data includes at least one of the following information: relevant information of the second NAS function body, the operating status of the second AIF, the operating status of the second DTF, and supporting data required for the AI ​​operation of the OAM.

[0024] In addition, according to at least one embodiment of the present invention, the second DTF is further used to perform at least one of the following functions when simulating the function of the corresponding second NAS function body: predicting the state of the corresponding second NAS function body, decomposing the computational load of the corresponding second NAS function body, pre-executing control signaling to minimize the end-to-end control cost and select a control signaling scheme, and selecting an optimal logical path for collaboration between the second NAS functions of the core network.

[0025] Furthermore, according to at least one embodiment of the present invention, the second DTF includes at least one second DT system, each second DT system emulating a second NAS function body;

[0026] The second AIF includes a second distributed AI system corresponding to each of the second DT systems, wherein the second distributed AI system, the first distributed AI system and the third distributed AI system are different parts of the distributed AI function, which jointly execute a predetermined AI algorithm or a predetermined task, and the first distributed AI system is a distributed AI system arranged at the terminal NAS layer.

[0027] In addition, according to at least one embodiment of the present invention, the second DT system is used to perform online simulation of the corresponding second NAS functional body under the unified control or management of the third DT system in the operation and maintenance system, and the third 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;

[0028] The second distributed AI system is used to operate under the unified control of the third distributed AI system in the operation and maintenance system, and to execute the predetermined AI algorithm or predetermined task based on information obtained from the interaction by interacting with the first distributed AI system and / or the third distributed AI system.

[0029] In addition, according to at least one embodiment of the present invention, the second DT system synchronizes information with the corresponding second NAS functional body by sharing data cache or operation information cache, or by data and information sharing.

[0030] In addition, according to at least one embodiment of the present invention, the second DT system is further used to receive third information and / or fourth information, and based on the third information and / or fourth information, online simulate the operation of the corresponding second NAS function body, and under the drive of the AI ​​algorithm provided by the second distributed AI system, generate signaling, policies and commands for the second NAS function body and send them to the corresponding second NAS function body for processing; wherein the third information is input information of the corresponding second NAS function body, and the fourth information is information generated during the operation of the corresponding second NAS function body.

[0031] In addition, according to at least one embodiment of the present invention, the second DTF further includes a second controller and a fifth distributed AI system, wherein:

[0032] The second controller is used to control and arrange the functions of each second DT system under the drive of the fifth distributed AI system.

[0033] Furthermore, according to at least one embodiment of the present invention, the fifth distributed AI system is used to select at least one alternative optimization solution and provide it to the controller based on the input information and the characteristics of each second DT system;

[0034] The second controller is also used to select one or more candidate optimization schemes from the alternative optimization schemes, and configure them to the corresponding second DT system for operation, and select a final optimization scheme based on the operation results of the candidate optimizations, and send configuration information to the relevant second NAS function body through signaling, policy or command based on the final optimization scheme.

[0035] In addition, according to at least one embodiment of the present invention, the second DTF further includes a second data or information sharing function and a sixth distributed AI system;

[0036] The sixth distributed AI system is used to use an AI algorithm to optimize the information stored in the second data or information sharing functional body, and record the data or information obtained after the optimization iteration to provide it to each second DT system for use.

[0037] According to another aspect of the present invention, at least one embodiment provides a method for implementing endogenous intelligence and digital twins of a non-access layer, which is applied to a terminal, wherein the non-access layer NAS of the terminal includes a first digital twin function DTF and / or a first artificial intelligence function AIF; the method includes:

[0038] The first AIF of the terminal provides AI capability driving for the first DTF under the control or management of the third distributed AI system in the operation and maintenance system;

[0039] The first DTF of the terminal synchronously obtains relevant information of the first NAS function body, drives by using the AI ​​capability provided by the first distributed AIF, simulates the function of the first NAS function body online, and obtains first measurement data and reports the first measurement data to the second DTF in the core network, where the first measurement data includes at least one of the following information: relevant information of the first NAS function body, the operating status of the first AIF, the operating status of the first DTF, and supporting data required for AI operation on the network side.

[0040] In addition, according to at least one embodiment of the present invention, the first DTF of the terminal, when simulating the function of the corresponding first NAS function body, performs at least one of the following functions: predicting the state of the corresponding first NAS function body, decomposing the computational load of the corresponding first NAS function body, pre-executing control signaling to minimize the end-to-end control cost and select a control signaling scheme, and selecting an optimal logical path for collaboration between the first NAS functions of the terminal.

[0041] According to another aspect of the present invention, at least one embodiment provides a method for implementing endogenous intelligence and digital twins of a non-access layer, which is applied to a core network, wherein the non-access layer NAS of the core network includes a second DTF and / or a second AIF; wherein the method includes:

[0042] The second AIF of the core network provides an AI capability driver for the second DTF under the control or management of a third distributed AI system in the operation and maintenance system;

[0043] The second DTF of the core network synchronously obtains relevant information of the second NAS function body, and receives the first measurement data reported by the terminal; uses the AI ​​capability provided by the second distributed AIF to drive, based on the relevant information of the second NAS function body and the first measurement data, online simulates the function of the second NAS function body; and obtains the second measurement data and reports the second measurement data to the third DTF in the OAM, where the second measurement data includes at least one of the following information: relevant information of the second NAS function body, the operating status of the second AIF, the operating status of the second DTF, and supporting data required for the AI ​​operation of the OAM.

[0044] In addition, according to at least one embodiment of the present invention, the present invention further comprises:

[0045] The second DTF of the core network, when simulating the function of the corresponding second NAS function body, performs at least one of the following functions: predicting the state of the corresponding second NAS function body, decomposing the computational load of the corresponding second NAS function body, pre-executing control signaling to minimize the end-to-end control cost and select a control signaling scheme, and selecting an optimal logical path for collaboration between the second NAS functions of the core network.

[0046] According to another aspect of the present invention, at least one embodiment provides a terminal, 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 method when executed by the processor.

[0047] According to another aspect of the present invention, at least one embodiment provides a core network, including: 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.

[0048] According to another aspect of the present invention, at least one embodiment provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method described above are implemented.

[0049] According to another aspect of the present invention, at least one embodiment provides a computer-readable storage medium having a program stored thereon, and when the program is executed by a processor, the steps of the method described above are implemented.

[0050] Compared with the prior art, the implementation method and device of the endogenous wisdom and digital twin of the non-access layer provided by the embodiment of the present invention defines the functions of DTF and AIF and the NAS architecture as well as the logical relationship between the related functional bodies, and provides the interaction process between DTF and AIF on the UE side and the network side, realizing the NAS function facing the endogenous AI (Native AI), and realizing the function of AI driving the NAS layer. In addition, the endogenous NAS layer DTF function provided by the embodiment of the present invention realizes the driving of the NAS function by online simulation. The embodiment of the present invention can maximize the driving force of AI through the deep combination of Native AI and Native DT at the NAS layer. In addition, the embodiment of the present invention also realizes a distributed AI system with end-to-end unified control, which reduces the interaction of the message volume between interfaces and ensures the security of the information reported by the UE; and the end-to-end unified control of AI and DT can realize the software and configurability on the terminal side. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0052] Figure 1 A schematic diagram of a NAS functional architecture of endogenous intelligence and digital twins according to an embodiment of the present invention;

[0053] Figure 2 Schematic diagram of interaction between various functional bodies of DTF and NAS according to an embodiment of the present invention;

[0054] Figure 3 A schematic diagram of a logical architecture inside the NTF of an embodiment of the present invention;

[0055] Figure 4 A schematic diagram of the structure of a terminal provided by an embodiment of the present invention;

[0056] Figure 5 Another schematic diagram of the structure of a terminal provided by an embodiment of the present invention;

[0057] Figure 6 A schematic diagram of the structure of a core network provided by an embodiment of the present invention;

[0058] Figure 7 Another structural diagram of a core network provided by an embodiment of the present invention;

[0059] Figure 8 A flow chart of the method for implementing the endogenous wisdom and digital twin of the non-access layer according to an embodiment of the present invention when applied to a terminal;

[0060] Fig. 9 A flow chart of the method for realizing endogenous wisdom and digital twins of the non-access layer according to an embodiment of the present invention when applied to a core network;

[0061] Fig.10 An example diagram of the end-to-end endogenous intelligent NAS layer interaction process of an embodiment of the present invention;

[0062] Fig.11 A schematic diagram of another structure of a terminal provided by an embodiment of the present invention;

[0063] Fig.12 Another structural diagram of a core network provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0064] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the 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. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0065] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and need not be 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 can be implemented in a sequence other than those illustrated or described herein, for example. In addition, the terms "including" and "having" 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 inherent to these processes, methods, products or equipment. "And / or" in the specification and claims represents at least one of the connected objects.

[0066] 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 functions and arrangements of the elements discussed without departing from the spirit and scope of the present disclosure. Various examples may appropriately omit, replace, 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.

[0067] In the research of 6G network, endogenous intelligence and digital twins have become the core features of 6G network. 6G network is considered to be a network with endogenous intelligence (Native AI). In the 6G network with endogenous intelligence, AI is no longer just the optimization of wireless resources of wireless network, but an intelligent system (AI System) integrated with core network, transmission network and wireless access.

[0068] The 6G digital twin system (DT) provides a basic operating environment for 6G endogenous intelligence, which provides basic support for AI-related processing and computing, and simplifies the operating load and complexity of the physical network. In other words, the 6G digital twin system and the endogenous intelligence system together constitute a series of online operations such as operation, maintenance, and application-oriented control computing for the physical network, becoming the brain of the physical network, commanding each part of the physical network to complete the service capabilities required by the protocol or operator.

[0069] As described in the background technology, the AI ​​in the 4G / 5G network of the prior art is an external AI, which runs in the OAM system. There are problems such as high cost of information reporting and the strategy generated by AI may be difficult to match network needs. In order to solve at least one of the above problems, the embodiment of the present invention proposes an implementation scheme of endogenous intelligence and digital twins in the non-access layer, and realizes endogenous intelligence and digital twin functions in the non-access layer. On the terminal side, the inter-layer division is performed according to NAS and access stratum (Access Stratum, AS), and on the network side, it is divided according to core network (Core Network, CN) and radio access network (Radio Access Network, RAN). In this scheme, by introducing online digital twin functions and distributed AI functions in the NAS layer, and through the interaction and distributed control between NAS on the terminal side and the core network on the network side, the NAS scheme of endogenous intelligence and digital twins is realized.

[0070] Figure 1 A schematic diagram of the NAS functional architecture of the endogenous intelligence and digital twin of an embodiment of the present invention is provided. Figure 1 The Online DT and Offline DT in the figure represent online DT and offline DT respectively. Here, offline (Offline) and online (Online) reflect the synchronization relationship between the corresponding functional bodies, which has nothing to do with the traditional high / low real-time performance and fast / slow speed. For example, Offline DT can obtain high-real-time data within a period of time through recording and broadcasting, and then process the data to obtain the simulation results.

[0071] like Figure 1 As shown, the embodiment of the present invention introduces new functions in the NAS of the terminal (UE): an artificial intelligence function (AIFunction, AIF) and a digital twin function (Digital Twin Function, DTF). Figure 1 In the NAS layer on the UE side, there are NAS AIF and NASDTF that simulates various NAS functions (such as AMF / SMF / UPF / NSSF, etc.); the core network (CN) side includes DTF that simulates various NAS functions (such as AMF / SMF / UPF / NSSF, etc.). Here, AMF is the Access and Mobility Management Function, SMF is the Session Management Function, UPF is the User Plane Function, and NSSF is the Network Slice Selection Function.

[0072] Among them, the main function of DTF is to synchronously obtain the input information or output information of the corresponding NAS functional body, operation monitoring information, processed data information, processed signaling information, etc., and through online simulation of the functions of the NAS functional body, realize the prediction of the normal or abnormal state of the NAS functional body and the early decomposition of the load of complex operations, thereby reducing the system overhead during online operation, pre-execution of control signaling to minimize the end-to-end control cost and the selection of control signaling schemes, and the selection of the optimal logical path for collaboration between various functional bodies.

[0073] DTF performs online simulation under the unified control or management of the offline DT system (Offline DT) of the OAM system. The online DT (Online DT) in DTF and the offline DT (Offline DT) in the OAM system are relative. Because the DT in DTF runs synchronously with each NAS function, it is called Online DT; while the DT in the OAM system does not need to run synchronously with each function, so it is called Offline DT.

[0074] The distributed AI (algorithm) running in the AIF of the NAS layer runs under the unified control of the distributed AI function in the OAM system. Distributed AI means that the AI ​​algorithms between the OAM system and the NAS system are logically different parts of a complete algorithm, or a logical constraint relationship that must be maintained in order to complete a task.

[0075] In NAS, the online simulation function body for each NAS function body in DTF can realize synchronous operation with the NAS function body by sharing data cache or operation information cache, synchronous sharing of data and information, etc.

[0076] Figure 2 Provides a closed-loop relationship between DTF and NAS functional bodies, such as Figure 2 As shown in the figure, the synchronous operation relationship between the various functional bodies of DTF and NAS includes:

[0077] 201: Input of each NAS function body (such as AMF / SMF / UPF / NSSF, etc.) is input into the corresponding online simulation function body in DTF at the same time as each NAS function body is input. The input information includes signaling, data packets, measurement information, operation and maintenance instructions, etc. In addition, in order to reduce the overhead of running DTF, key information can be input into DTF, and non-essential information can be discarded. For example, for data packets (IP packets), the valid packet header can be input into DTF, and the net load (Payload) of the data packet can be omitted.

[0078] 202: During the operation of each NAS function, the key information of the operation process is reported to the DTF. For example, when processing a data packet, the information of whether the data packet is received successfully and the data size; when receiving a signaling, the information of the change caused by the signaling to the operation of the NAS function (the signaling configuration of the function operation before the signaling takes effect), the state information of the function operation when the signaling is received, etc.

[0079] 203: DTF simulates the operation of each NAS functional body online according to the input information, and generates signaling, policy or command for different NAS functional bodies under the drive of AI algorithm.

[0080] 204: The signaling, policy or command generated by the DTF is input into the NAS function body as feedback; each NAS function body performs low-cost or low-overhead fast processing according to the input signaling, policy or command.

[0081] 205-206: Each NAS function body outputs its own operation result, and the operation result can also be input into the corresponding online simulation function body in DTF.

[0082] Please refer to Figure 3 , provides a schematic diagram of the logical architecture inside NTF. DTF includes various NAS online simulation function bodies, such as AMF online simulation function body (Online DT:AMF), SMF online simulation function body (Online DT:SMF), UPF online simulation function body (Online DT:UPF), NSSF online simulation function body (Online DT:NSSF), etc., and also includes controller (Controller) and data or information sharing function body (Data / Informationsharing). In addition, each function body has a corresponding AI function driver.

[0083] Here, the controller controls and arranges the specific functions of each functional body of the online simulation under the drive of the distributed AI function. When optimizing the process or processing that needs to pass through one or more functional bodies of the NAS layer, the controller makes a configuration selection based on the input information, and then configures it to each functional body of the online simulation. The distributed AI function here selects one or more optimization schemes for the controller based on the input information and the characteristics of each functional body of the online simulation. The controller makes one or more selections based on the alternative optimization schemes, and configures them to the corresponding online simulation functional body. It selects the final optimization scheme based on the running results and sends it to the NAS-related functional body through signaling, policy or command.

[0084] Each online simulation function body is set according to the actual function body of NAS, such as AMF, SMF, NSSF, UPF, etc.

[0085] Each online simulation function has a corresponding distributed AI function, which has the capability of one or more AI algorithms. These distributed AI algorithms provide AI capability drive to each online function under the control or management of the distributed AI algorithm of the OAM system. Here, AI capability drive refers to strengthening related functions under the AI ​​algorithm, or realizing one or more online functions based on the AI ​​algorithm.

[0086] The distributed AI function running on shared information (Data / Information Sharing) mainly uses AI algorithms to optimize the data of the above-mentioned stored information, and records the optimized and iterated data or information for use by various online simulation function bodies.

[0087] The core network side includes a unified data management (UDM) module. The UDM module has a corresponding distributed AI function body. The distributed AI function body is mainly data-oriented, uses AI algorithms to optimize data, and records the optimized and iterated data or information for use by the entire NAS layer function body.

[0088] Based on the above functional architecture, an embodiment of the present invention provides a terminal such as Figure 4 As shown, the NAS of the terminal includes a first DTF and / or a first AIF; wherein,

[0089] A first AIF 41, configured to provide an AI capability driver for the first DTF under the control or management of a third distributed AI system in the operation and maintenance system;

[0090] The first DTF 42 is used to synchronously obtain relevant information of the first NAS function body, and use the AI ​​capability provided by the first distributed AIF to drive the function of the first NAS function body online, and obtain first measurement data and report the first measurement data to the second DTF in the core network, where the first measurement data includes at least one of the following information: relevant information of the first NAS function body, the operating status of the first AIF, the operating status of the first DTF, and supporting data required for AI operation on the network side.

[0091] Here, the first DTF is further used to perform at least one of the following functions when simulating the function of the corresponding first NAS function body: predicting the state of the corresponding first NAS function body, decomposing the computing load of the corresponding first NAS function body, pre-executing control signaling to minimize the end-to-end control cost and select a control signaling scheme, and selecting an optimal logical path for collaboration between the first NAS functions of the terminal.

[0092] like Figure 5 As shown, the first DTF 42 includes at least one first DT system 421, and each first DT system 421 simulates a first NAS function body;

[0093] The first AIF 41 includes a first distributed AI system 411 corresponding to each of the first DT systems 421, wherein the first distributed AI system, the second distributed AI system and the third distributed AI system are different parts of the distributed AI function, which jointly execute a predetermined AI algorithm or a predetermined task, and the second distributed AI system is a distributed AI system arranged in the core network.

[0094] Here, the first DT system 421 is used to perform online simulation of the corresponding first NAS functional body under the unified control or management of the third DT system in the operation and maintenance system. The third 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.

[0095] The first distributed AI system 411 is used to operate under the unified control of the third distributed AI system in the operation and maintenance system, and to execute the predetermined AI algorithm or predetermined task according to the information obtained through information interaction with the second distributed AI system and / or the third distributed AI system.

[0096] In the embodiment of the present invention, the first DT system may perform information synchronization with the corresponding first NAS function body by sharing data cache or operation information cache, or by data and information sharing.

[0097] In addition, the first DT system is also used to receive the first information and / or the second information, and according to the first information and / or the second information, online simulate the operation of the corresponding first NAS function body, and under the drive of the AI ​​algorithm provided by the first distributed AI system, generate signaling, policies and commands for the first NAS function body and send them to the corresponding first NAS function body for processing; wherein the first information is the input information of the corresponding first NAS function body, and the second information is the information generated during the operation of the corresponding first NAS function body.

[0098] In the embodiment of the present invention, the first DTF may further include a first controller and a third distributed AI system, wherein the first controller is configured to control and arrange the functions of each first DT system under the drive of the third distributed AI system.

[0099] Here, the third distributed AI system is used to select at least one alternative optimization scheme based on the input information and the characteristics of each first DT system and provide it to the controller; the first controller is also used to select one or more candidate optimization schemes from the alternative optimization schemes, and configure them to the corresponding first DT system for operation, and select a final optimization scheme based on the operation results of the candidate optimizations, and send configuration information to the relevant first NAS functional body through signaling, policy or command based on the final optimization scheme.

[0100] In the embodiment of the present invention, the first DTF may further include a first data or information sharing functional body and a fourth distributed AI system. The fourth distributed AI system is used to use an AI algorithm to optimize the information stored in the first data or information sharing functional body, and record the data or information obtained after the optimization iteration to provide it to each first DT system for use.

[0101] Please refer to Figure 6 The embodiment of the present invention further provides a core network, which may be a network element or node of the core network, such as Figure 5 As shown, the core network includes a second DTF 62 and / or a second AIF 61; wherein,

[0102] The second AIF 61 is used to provide an AI capability driver for the second DTF under the control or management of a third distributed AI system in the operation and maintenance system;

[0103] The second DTF 62 is used to synchronously obtain relevant information of the second NAS function body and receive the first measurement data reported by the terminal; use the AI ​​capability provided by the second distributed AIF to drive, based on the relevant information of the second NAS function body and the first measurement data, online simulate the function of the second NAS function body; and obtain the second measurement data and report the second measurement data to the third DTF in the OAM, where the second measurement data includes at least one of the following information: relevant information of the second NAS function body, the operating status of the second AIF, the operating status of the second DTF, and supporting data required for the AI ​​operation of the OAM.

[0104] Here, the second DTF is further used to perform at least one of the following functions when simulating the function of the corresponding second NAS function body: predicting the state of the corresponding second NAS function body, decomposing the computing load of the corresponding second NAS function body, pre-executing control signaling to minimize the end-to-end control cost and select a control signaling scheme, and selecting an optimal logical path for collaboration between the second NAS functions of the core network.

[0105] like Figure 7 As shown, the second DTF 62 includes at least one second DT system 621, and each second DT system 621 simulates a second NAS function body;

[0106] The second AIF 61 includes a second distributed AI system 611 corresponding to each of the second DT systems 621, wherein the second distributed AI system, the first distributed AI system and the third distributed AI system are different parts of the distributed AI function, which jointly execute a predetermined AI algorithm or a predetermined task, and the first distributed AI system is a distributed AI system set at the terminal NAS layer.

[0107] Here, the second DT system is used to perform online simulation of the corresponding second NAS functional body under the unified control or management of the third DT system in the operation and maintenance system. The third 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.

[0108] The second distributed AI system is used to operate under the unified control of the third distributed AI system in the operation and maintenance system, and to execute the predetermined AI algorithm or predetermined task based on information obtained from the interaction by interacting with the first distributed AI system and / or the third distributed AI system.

[0109] In addition, the second DT system may also synchronize information with the corresponding second NAS functional body by sharing data cache or operation information cache, or by data and information sharing.

[0110] In an embodiment of the present invention, the second DT system is further used to receive third information and / or fourth information, and according to the third information and / or fourth information, online simulate the operation of the corresponding second NAS function body, and under the drive of the AI ​​algorithm provided by the second distributed AI system, generate signaling, policies and commands for the second NAS function body and send them to the corresponding second NAS function body for processing; wherein the third information is input information of the corresponding second NAS function body, and the fourth information is information generated during the operation of the corresponding second NAS function body.

[0111] In addition, the second DTF also includes a second controller and a fifth distributed AI system, wherein the second controller is used to control and arrange the functions of each second DT system under the drive of the fifth distributed AI system.

[0112] Here, the fifth distributed AI system is used to select at least one alternative optimization scheme according to the input information and the characteristics of each second DT system and provide it to the controller. The second controller is also used to select one or more candidate optimization schemes from the alternative optimization schemes, and configure them to the corresponding second DT system for operation, and select a final optimization scheme according to the operation results of the candidate optimization, and send configuration information to the relevant second NAS function body through signaling, policy or command according to the final optimization scheme.

[0113] In the embodiment of the present invention, the second DTF further includes a second data or information sharing functional body and a sixth distributed AI system. The sixth distributed AI system is used to use an AI algorithm to optimize the information stored in the second data or information sharing functional body, and record the data or information obtained after the optimization iteration to provide it to each second DT system for use.

[0114] Based on the above functional architecture, an embodiment of the present invention further provides a method for realizing endogenous intelligence and digital twins of a non-access layer, which is applied to a terminal, wherein the non-access layer NAS of the terminal includes a first digital twin function DTF and / or a first artificial intelligence function AIF. Figure 8 As shown, the method includes:

[0115] Step 81: The first AIF of the terminal provides AI capability driving for the first DTF under the control or management of the third distributed AI system in the operation and maintenance system;

[0116] In step 82, the first DTF of the terminal synchronously obtains relevant information of the first NAS function body, and uses the AI ​​capability provided by the first distributed AIF to drive the online simulation of the function of the first NAS function body, and obtains first measurement data and reports the first measurement data to the second DTF in the core network, where the first measurement data includes at least one of the following information: relevant information of the first NAS function body, the operating status of the first AIF, the operating status of the first DTF, and supporting data required for AI operation on the network side.

[0117] Through the above steps, the embodiment of the present invention realizes a non-access layer with inherent intelligence and digital twin functions, and can reduce the overhead of information reporting between the operation and maintenance system and the managed objects.

[0118] Optionally, in the embodiment of the present invention, the first DTF of the terminal, when simulating the function of the corresponding first NAS function body, performs at least one of the following functions: predicting the state of the corresponding first NAS function body, decomposing the computing load of the corresponding first NAS function body, pre-executing control signaling to minimize the end-to-end control cost and select a control signaling scheme, and selecting an optimal logical path for collaboration between the first NAS function bodies of the terminal.

[0119] Optionally, the first DTF includes at least one first DT system, each first DT system simulating a first NAS functional body; the first AIF includes a first distributed AI system corresponding to each of the first DT systems, wherein the first distributed AI system, the second distributed AI system and the third distributed AI system are different parts of the distributed AI function, and jointly execute a predetermined AI algorithm or a predetermined task, and the second distributed AI system is a distributed AI system arranged in the core network.

[0120] Optionally, the first DT system performs online simulation of the corresponding first NAS functional body under the unified control or management of the third DT system in the operation and maintenance system, and the third 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; the first distributed AI system runs under the unified control of the third distributed AI system in the operation and maintenance system, and executes the predetermined AI algorithm or predetermined task based on the information obtained from the interaction by exchanging information with the second distributed AI system and / or the third distributed AI system.

[0121] Optionally, the first DT system synchronizes information with the corresponding first NAS functional body by sharing data cache or running information cache, or by data and information sharing.

[0122] Optionally, the first DT system may also receive the first information and / or the second information, and based on the first information and / or the second information, online simulate the operation of the corresponding first NAS functional body, and, driven by the AI ​​algorithm provided by the first distributed AI system, generate signaling, policies and commands for the first NAS functional body and send them to the corresponding first NAS functional body for processing; wherein the first information is input information corresponding to the first NAS functional body, and the second information is information generated during the operation of the corresponding first NAS functional body.

[0123] Optionally, the first DTF also includes a first controller and a third distributed AI system, wherein the first controller, driven by the third distributed AI system, controls and arranges functions of each first DT system.

[0124] Optionally, the third distributed AI system selects at least one alternative optimization scheme based on the input information and the characteristics of each first DT system and provides it to the controller. The first controller also selects one or more candidate optimization schemes from the alternative optimization schemes, and configures them to the corresponding first DT system for operation, and selects a final optimization scheme based on the operation results of the candidate optimizations, and sends configuration information to the relevant first NAS function body through signaling, policy or command based on the final optimization scheme.

[0125] Optionally, the first DTF also includes a first data or information sharing functional body and a fourth distributed AI system; the fourth distributed AI system uses an AI algorithm to optimize the information stored in the first data or information sharing functional body, and records the data or information obtained after the optimization iteration to provide it to each first DT system for use.

[0126] The embodiment of the present invention further provides a method for realizing endogenous wisdom and digital twin of a non-access layer, which is applied to a core network, wherein the non-access layer NAS of the core network includes a second DTF and / or a second AIF; Fig. 9 As shown, the method includes:

[0127] Step 91: The second AIF of the core network provides AI capability driving for the second DTF under the control or management of the third distributed AI system in the operation and maintenance system.

[0128] In step 92, the second DTF of the core network synchronously obtains relevant information of the second NAS function body and receives the first measurement data reported by the terminal; uses the AI ​​capability provided by the second distributed AIF to drive, based on the relevant information of the second NAS function body and the first measurement data, online simulates the function of the second NAS function body; and obtains the second measurement data and reports the second measurement data to the third DTF in the OAM, where the second measurement data includes at least one of the following information: relevant information of the second NAS function body, the operating status of the second AIF, the operating status of the second DTF, and supporting data required for the AI ​​operation of the OAM.

[0129] Optionally, in an embodiment of the present invention, the second DTF of the core network, when simulating the function of the corresponding second NAS functional body, performs at least one of the following functions: predicting the state of the corresponding second NAS functional body, decomposing the computing load of the corresponding second NAS functional body, pre-executing control signaling to minimize the end-to-end control cost and select a control signaling scheme, and selecting the optimal logical path for collaboration between the second NAS functional bodies of the core network.

[0130] Optionally, in an embodiment of the present invention, the second DTF includes at least one second DT system, each second DT system simulates a second NAS functional body; the second AIF includes a second distributed AI system corresponding to each of the second DT systems, wherein the second distributed AI system, the first distributed AI system and the third distributed AI system are different parts of the distributed AI function, and jointly execute a predetermined AI algorithm or a predetermined task, and the first distributed AI system is a distributed AI system set at the terminal NAS layer.

[0131] Optionally, in an embodiment of the present invention, the second DT system performs online simulation of the corresponding second NAS functional body under the unified control or management of the third DT system in the operation and maintenance system, and the third 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; the second distributed AI system runs under the unified control of the third distributed AI system in the operation and maintenance system, and executes the predetermined AI algorithm or predetermined task based on the information obtained from the interaction by exchanging information with the first distributed AI system and / or the third distributed AI system.

[0132] Optionally, in an embodiment of the present invention, the second DT system synchronizes information with the corresponding second NAS functional body by sharing data cache or operation information cache, or by data and information sharing.

[0133] Optionally, in an embodiment of the present invention, the second DT system may also receive third information and / or fourth information, and based on the third information and / or fourth information, online simulate the operation of the corresponding second NAS functional body, and, driven by the AI ​​algorithm provided by the second distributed AI system, generate signaling, policies and commands for the second NAS functional body and send them to the corresponding second NAS functional body for processing; wherein the third information is input information of the corresponding second NAS functional body, and the fourth information is information generated during the operation of the corresponding second NAS functional body.

[0134] Optionally, in an embodiment of the present invention, the second DTF also includes a second controller and a fifth distributed AI system, wherein the second controller, driven by the fifth distributed AI system, controls and arranges the functions of each second DT system.

[0135] Optionally, in an embodiment of the present invention, the fifth distributed AI system selects at least one alternative optimization scheme based on the input information and the characteristics of each second DT system and provides it to the controller; the second controller may also select one or more candidate optimization schemes from the alternative optimization schemes, and configure them to the corresponding second DT system for operation, and select a final optimization scheme based on the operation results of the candidate optimizations, and send configuration information to the relevant second NAS functional body through signaling, policy or command based on the final optimization scheme.

[0136] Optionally, in an embodiment of the present invention, the second DTF also includes a second data or information sharing functional body and a sixth distributed AI system; the sixth distributed AI system uses an AI algorithm to optimize the information stored in the second data or information sharing functional body, and records the data or information obtained after the optimization iteration to provide it to each second DT system for use.

[0137] Please refer to Fig.10 , provides an example of an end-to-end endogenous intelligent NAS layer interaction process implemented based on the functional architecture of an embodiment of the present invention, wherein DTF_UE represents DTF on the UE side, DTF_CN represents DTF on the core network side, and AIF_CN represents AIF on the core network side. Fig.10 As shown in the figure, the interaction process between the UE side and the CN side under the unified control and management of OAM includes:

[0138] Step 100, the OAM system performs initial configuration on the core network (CN), including the initial startup parameters of the DTF, the online simulation function body, the minimized running function configuration, etc.; configures the initial AI algorithm set for the AIF, the online simulation function body of the service, etc.

[0139] Step 101, a connection is established between the NAS layer of the UE and the NAS function of the core network (CN). The UE can report its supported DTF and AIF capabilities to the network side, including the maximum computing power consumed by the supported DTF calculation, the maximum data cache capacity, the accuracy that can be achieved by the calculation, the type of AI algorithm, the calculation scale, etc.

[0140] Step 102: When the UE establishes a NAS layer connection, the DTF and AIF of the CN initiate configuration for the UE to the OAM, specifically including configuring the AIF and DTF capabilities or function sets available to the UE. The AIF and DTF capabilities or function sets available to the UE are obtained by taking the intersection between the AIF and DTF capabilities reported by the UE and the AIF and DTF capabilities supported by the network itself.

[0141] Step 103, the OAM system configures the AIF and DTF configuration information for the UE to the AIF and DTF of the core network, including: the functional body of the DTF online simulation, the achieved performance, the calculation accuracy, etc.; the AI ​​algorithm set of the AIF, the calculation scale, etc.

[0142] Step 104: CN allocates the configuration information of the AIF and DTF of the UE to the UE through NAS signaling, including: the AI ​​capability or function set, DT capability or function set, etc. available to the UE.

[0143] Here, the AI ​​capability or function set, DT capability or function set available to the UE is the intersection of the AI ​​capability or function set, DT capability or function set supported by the UE and the AI ​​capability or function set, DT capability or function set supported by the network side. The process of obtaining this intersection is the process of interaction between the UE and the network side through NAS signaling. For example, the UE first initiates an application, and the network side configures the available intersection content according to the UE's application.

[0144] In steps 105-106, the DTF or AIF of the UE reports various measurement information to the network side, and the network side performs AI calculation based on the measurement information reported by the UE and reports it to the OAM system. The measurement information reported by the UE can be used to synchronize the operation status of its AIF and DTF to the network side, as well as the AI ​​operation support data that needs to be reported to the network side according to the requirements of the distributed AI function.

[0145] The implementation scheme of the endogenous wisdom and digital twin of the non-access layer provided by the embodiment of the present invention defines the functions of DTF and AIF and the NAS architecture as well as the logical relationship between the related functional bodies, and provides the interaction process between DTF and AIF on the UE side and the network side, realizing the NAS function for endogenous AI (Native AI), and realizing the function of AI driving the NAS layer. In addition, the endogenous NAS layer DTF function provided by the embodiment of the present invention realizes the driving of the NAS function by online simulation. The embodiment of the present invention can maximize the driving force of AI through the deep combination of Native AI and Native DT at the NAS layer. In addition, the embodiment of the present invention realizes a distributed AI system with end-to-end unified control, reduces the interaction of the message volume between interfaces, and ensures the security of the information reported by the UE; and the end-to-end unified control of AI and DT can realize software and configurability on the terminal side.

[0146] Please refer to Fig.11 , a schematic diagram of a structure of a terminal provided in an embodiment of the present invention, the terminal includes: a processor 1101, a transceiver 1102, a memory 1103, a user interface and a bus interface.

[0147] In the embodiment of the present invention, the terminal further includes: a program stored in the memory 1103 and executable on the processor 1101 .

[0148] When the processor 1101 executes the program, the following steps are implemented:

[0149] Providing AI capability driving for the first DTF through the first AIF of the terminal under the control or management of a third distributed AI system in the operation and maintenance system;

[0150] Through the first DTF of the terminal, synchronously obtain relevant information of the first NAS function body, and use the AI ​​capability provided by the first distributed AIF to drive the function of the first NAS function body online, and obtain first measurement data and report the first measurement data to the second DTF in the core network, where the first measurement data includes at least one of the following information: relevant information of the first NAS function body, the operating status of the first AIF, the operating status of the first DTF, and supporting data required for AI operation on the network side.

[0151] exist Fig.11In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 1101 and various circuits of memory represented by memory 1103 are linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 1102 may be a plurality of components, namely, 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 externally and internally connecting required devices, and the connected devices include but are not limited to a keypad, a display, a speaker, a microphone, a joystick, and the like.

[0152] The processor 1101 is responsible for managing the bus architecture and general processing, and the memory 1103 can store data used by the processor 1101 when performing operations.

[0153] 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, the implementation methods in the above embodiments are all applicable to the embodiments of the device, and can also achieve the same technical effect. In the device, the transceiver 1102 and the memory 1103, as well as the transceiver 1102 and the processor 1101 can be connected through the bus interface communication, the function of the processor 1101 can also be implemented by the transceiver 1102, and the function of the transceiver 1102 can also be implemented by the processor 1101. It should be noted that the above device provided in the embodiment of the present invention can implement all the method steps implemented in the above method embodiment, and can achieve the same technical effect, and the parts and beneficial effects that are the same as the method embodiment in this embodiment will not be specifically repeated here.

[0154] In some embodiments of the present invention, a computer-readable storage medium is further provided, on which a program is stored, and when the program is executed by a processor, the following steps are implemented:

[0155] Providing AI capability driving for the first DTF through the first AIF of the terminal under the control or management of the third distributed AI system in the operation and maintenance system;

[0156] Through the first DTF of the terminal, synchronously obtain relevant information of the first NAS function body, and use the AI ​​capability provided by the first distributed AIF to drive the function of the first NAS function body online, and obtain first measurement data and report the first measurement data to the second DTF in the core network, where the first measurement data includes at least one of the following information: relevant information of the first NAS function body, the operating status of the first AIF, the operating status of the first DTF, and supporting data required for AI operation on the network side.

[0157] When the program is executed by the processor, it can implement all the implementation methods of the above-mentioned endogenous wisdom and digital twins applied to the non-access layer of the terminal, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0158] Please refer to Fig.12 , an embodiment of the present invention provides a schematic diagram of a core network structure, including: a processor 1201, a transceiver 1202, a memory 1203 and a bus interface, wherein:

[0159] In the embodiment of the present invention, the core network further includes: a program stored in the memory 1203 and executable on the processor 1201, wherein the program implements the following steps when executed by the processor 1201:

[0160] Providing AI capability drive for the second DTF through the second AIF of the core network under the control or management of the third distributed AI system in the operation and maintenance system;

[0161] Through the second DTF of the core network, synchronously obtain relevant information of the second NAS function body, and receive the first measurement data reported by the terminal; use the AI ​​capability provided by the second distributed AIF to drive, based on the relevant information of the second NAS function body and the first measurement data, online simulate the function of the second NAS function body; and obtain the second measurement data and report the second measurement data to the third DTF in the OAM, where the second measurement data includes at least one of the following information: relevant information of the second NAS function body, the operating status of the second AIF, the operating status of the second DTF, and supporting data required for the AI ​​operation of the OAM.

[0162] exist Fig.12 In 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 1201 and memory represented by memory 1203. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 1202 may be a plurality of components, namely, a transmitter and a receiver, providing a unit for communicating with various other devices over a transmission medium.

[0163] The processor 1201 is responsible for managing the bus architecture and general processing, and the memory 1203 can store data used by the processor 1201 when performing operations.

[0164] It should be noted that the terminal in this embodiment is the same as the above Figure 5The device corresponding to the method shown, the implementation methods in the above embodiments are all applicable to the embodiments of the terminal, and can also achieve the same technical effect. In the device, the transceiver 1202 and the memory 1203, as well as the transceiver 1202 and the processor 1201 can be connected through the bus interface communication, the function of the processor 1201 can also be implemented by the transceiver 1202, and the function of the transceiver 1202 can also be implemented by the processor 1201. It should be noted that the above device provided in the embodiment of the present invention can implement all the method steps implemented in the above method embodiment, and can achieve the same technical effect, and the parts and beneficial effects that are the same as the method embodiment in this embodiment will not be specifically repeated here.

[0165] In some embodiments of the present invention, a computer-readable storage medium is further provided, on which a program is stored, and when the program is executed by a processor, the following steps are implemented:

[0166] Providing AI capability drive for the second DTF through the second AIF of the core network under the control or management of the third distributed AI system in the operation and maintenance system;

[0167] Through the second DTF of the core network, synchronously obtain relevant information of the second NAS function body, and receive the first measurement data reported by the terminal; use the AI ​​capability provided by the second distributed AIF to drive, based on the relevant information of the second NAS function body and the first measurement data, online simulate the function of the second NAS function body; and obtain the second measurement data and report the second measurement data to the third DTF in the OAM, where the second measurement data includes at least one of the following information: relevant information of the second NAS function body, the operating status of the second AIF, the operating status of the second DTF, and supporting data required for the AI ​​operation of the OAM.

[0168] When the program is executed by the processor, it can implement all the implementation methods of the above-mentioned endogenous wisdom and digital twin implementation methods applied to the non-access layer of the OAM system, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0169] 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. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0170] Those skilled in the art can 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.

[0171] In the embodiments provided in the present 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 only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, 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.

[0172] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.

[0173] 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.

[0174] If the functions are implemented in the form of 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 part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform 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 codes, such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical disks.

[0175] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A terminal, It is characterized in that The non-access layer NAS of the terminal includes a first digital twin function DTF and / or a first artificial intelligence function AIF; wherein, The first AIF is configured to provide an AI capability driver for the first DTF under the control or management of a third distributed AI system in the operation and maintenance system; The first DTF is used to synchronously obtain relevant information of the first NAS function body, and use the AI ​​capability provided by the first AIF to drive the online simulation of the function of the first NAS function body, and obtain first measurement data and report the first measurement data to the second DTF in the core network, where the first measurement data includes at least one of the following information: relevant information of the first NAS function body, the operating status of the first AIF, the operating status of the first DTF, and supporting data required for AI operation on the network side.

2. The terminal according to claim 1, It is characterized in that The first DTF is further configured to perform at least one of the following functions when simulating the function of the corresponding first NAS function body: predicting the state of the corresponding first NAS function body, decomposing the computational load of the corresponding first NAS function body, pre-executing control signaling to minimize the end-to-end control cost and select a control signaling scheme, and selecting an optimal logical path for collaboration between the first NAS functions of the terminal.

3. The terminal according to claim 1, It is characterized in that The first DTF includes at least one first DT system, each of which simulates a first NAS function body; The first AIF includes a first distributed AI system corresponding to each of the first DT systems, wherein the first distributed AI system, the second distributed AI system and the third distributed AI system are different parts of the distributed AI function, which jointly execute a predetermined AI algorithm or a predetermined task, and the second distributed AI system is a distributed AI system arranged in the core network.

4. The terminal according to claim 3, It is characterized in that The first DT system is used to perform online simulation of the corresponding first NAS functional body under the unified control or management of the third DT system in the operation and maintenance system, and the third 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; The first distributed AI system is used to operate under the unified control of the third distributed AI system in the operation and maintenance system, and to execute the predetermined AI algorithm or predetermined task based on information obtained from the interaction by interacting with the second distributed AI system and / or the third distributed AI system.

5. The terminal according to claim 3, It is characterized in that The first DT system synchronizes information with the corresponding first NAS function body by sharing data cache or running information cache, or by data and information sharing.

6. The terminal according to claim 3, It is characterized in that The first DT system is also used to receive the first information and / or the second information, and according to the first information and / or the second information, online simulate the operation of the corresponding first NAS function body, and under the drive of the AI ​​algorithm provided by the first distributed AI system, generate signaling, policies and commands for the first NAS function body and send them to the corresponding first NAS function body for processing; wherein the first information is the input information of the corresponding first NAS function body, and the second information is the information generated during the operation of the corresponding first NAS function body.

7. The terminal according to claim 3, It is characterized in that The first DTF also includes a first controller and a third distributed AI system, wherein: The first controller is used to control and arrange the functions of each first DT system under the drive of the third distributed AI system.

8. The terminal according to claim 7, It is characterized in that The third distributed AI system is used to select at least one alternative optimization solution based on the input information and the characteristics of each first DT system and provide it to the controller; The first controller is also used to select one or more candidate optimization schemes from the alternative optimization schemes, and configure them to the corresponding first DT system for operation, and select a final optimization scheme based on the operation results of the candidate optimizations, and send configuration information to the relevant first NAS function body through signaling, policy or command based on the final optimization scheme.

9. The terminal according to claim 7, It is characterized in that The first DTF also includes a first data or information sharing function and a fourth distributed AI system; The fourth distributed AI system is used to use an AI algorithm to optimize the information stored in the first data or information sharing functional body, and record the data or information obtained after the optimization iteration to provide it to each first DT system for use.

10. A core network, It is characterized in that The core network includes a second DTF and / or a second AIF; wherein, A second AIF is used to provide an AI capability driver for the second DTF under the control or management of a third distributed AI system in the operation and maintenance system; The second DTF is used to synchronously obtain relevant information of the second NAS function body and receive the first measurement data reported by the terminal; use the AI ​​capability provided by the second AIF to drive, based on the relevant information of the second NAS function body and the first measurement data, online simulate the function of the second NAS function body; and obtain the second measurement data and report the second measurement data to the third DTF in the OAM, where the second measurement data includes at least one of the following information: relevant information of the second NAS function body, the operating status of the second AIF, the operating status of the second DTF, and supporting data required for the AI ​​operation of the OAM.

11. The core network as claimed in claim 10, It is characterized in that The second DTF is further configured to perform at least one of the following functions when simulating the functions of the corresponding second NAS functional entity: predicting the state of the corresponding second NAS functional entity, decomposing the computing load of the corresponding second NAS functional entity, pre-executing control signaling to minimize the end-to-end control cost and select a control signaling scheme, and selecting an optimal logical path for cooperation among the second NAS functional entities of the core network.

12. The core network according to claim 10, wherein, the second DTF includes at least one second DT system, and each second DT system simulates a second NAS functional entity respectively; the second AIF includes a second distributed AI system corresponding to each second DT system, wherein the second distributed AI system, the first distributed AI system, and the third distributed AI system are different parts of the distributed AI function and jointly execute a predetermined AI algorithm or a predetermined task, and the first distributed AI system is a distributed AI system disposed at the terminal NAS layer.

13. The core network according to claim 12, wherein, the second DT system is configured to perform online simulation of the corresponding second NAS functional entity under the unified control or management of a third DT system in an operation and maintenance system, the third DT system is an offline DT system, and the offline DT system refers to a DT system that does not need to run synchronously with the functional entity to be simulated; the second distributed AI system is configured to run under the unified control of a third distributed AI system in an operation and maintenance system, and perform the predetermined AI algorithm or the predetermined task according to the information obtained through interaction with the first distributed AI system and / or the third distributed AI system.

14. The core network according to claim 12, wherein, the second DT system synchronizes information with the corresponding second NAS functional entity through a shared data cache or a running information cache, or through a data and information sharing method.

15. The core network according to claim 12, wherein, the second DT system is further configured to receive third information and / or fourth information, perform online simulation of the operation of the corresponding second NAS functional entity according to the third information and / or the fourth information, and generate signaling, policies, and commands for the second NAS functional entity and send them to the corresponding second NAS functional entity for processing under the drive of the AI algorithm provided by the second distributed AI system; wherein the third information is the input information of the corresponding second NAS functional entity, and the fourth information is the information generated during the operation of the corresponding second NAS functional entity.

16. The core network according to claim 12, wherein, the second DTF further includes a second controller and a fifth distributed AI system, wherein, the second controller is configured to control and orchestrate the functions of the second DT systems under the drive of the fifth distributed AI system.

17. The core network according to claim 16, wherein, The fifth distributed AI system is used to select at least one alternative optimization solution based on the input information and the characteristics of each second DT system and provide it to the controller; The second controller is also used to select one or more candidate optimization schemes from the alternative optimization schemes, and configure them to the corresponding second DT system for operation, and select a final optimization scheme based on the operation results of the candidate optimizations, and send configuration information to the relevant second NAS function body through signaling, policy or command based on the final optimization scheme.

18. The core network according to claim 16, It is characterized in that The second DTF also includes a second data or information sharing function and a sixth distributed AI system; The sixth distributed AI system is used to use an AI algorithm to optimize the information stored in the second data or information sharing functional body, and record the data or information obtained after the optimization iteration to provide it to each second DT system for use.

19. A method for realizing endogenous intelligence and digital twins in a non-access layer, applied to terminals, It is characterized in that The non-access layer NAS of the terminal includes a first digital twin function DTF and / or a first artificial intelligence function AIF; the method includes: The first AIF of the terminal provides AI capability driving for the first DTF under the control or management of the third distributed AI system in the operation and maintenance system; The first DTF of the terminal synchronously obtains relevant information of the first NAS function body, drives by using the AI ​​capability provided by the first AIF, simulates the function of the first NAS function body online, and obtains first measurement data and reports the first measurement data to the second DTF in the core network, where the first measurement data includes at least one of the following information: relevant information of the first NAS function body, the operating status of the first AIF, the operating status of the first DTF, and supporting data required for AI operation on the network side.

20. The method of claim 19, It is characterized in that Also includes: The first DTF of the terminal, when simulating the function of the corresponding first NAS function body, performs at least one of the following functions: predicting the state of the corresponding first NAS function body, decomposing the computational load of the corresponding first NAS function body, pre-executing control signaling to minimize the end-to-end control cost and select a control signaling scheme, and selecting an optimal logical path for collaboration between the first NAS functions of the terminal.

21. A method for realizing endogenous intelligence and digital twins in a non-access layer, applied to a core network, It is characterized in that The non-access layer NAS of the core network includes a second DTF and / or a second AIF; wherein the method includes: The second AIF of the core network provides an AI capability driver for the second DTF under the control or management of a third distributed AI system in the operation and maintenance system; The second DTF of the core network synchronously obtains relevant information of the second NAS function body, and receives the first measurement data reported by the terminal; uses the AI ​​capability provided by the second AIF to drive, based on the relevant information of the second NAS function body and the first measurement data, online simulates the function of the second NAS function body; and obtains the second measurement data and reports the second measurement data to the third DTF in the OAM, where the second measurement data includes at least one of the following information: relevant information of the second NAS function body, the operating status of the second AIF, the operating status of the second DTF, and supporting data required for the AI ​​operation of the OAM.

22. The method of claim 21, It is characterized in that Also includes: The second DTF of the core network, when simulating the function of the corresponding second NAS function body, performs at least one of the following functions: predicting the state of the corresponding second NAS function body, decomposing the computational load of the corresponding second NAS function body, pre-executing control signaling to minimize the end-to-end control cost and select a control signaling scheme, and selecting an optimal logical path for collaboration between the second NAS functions of the core network.

23. A terminal, It is 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 19 to 20 are implemented.

24. A core network, It is 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 21 to 22 are implemented.

25. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 19 to 22 are implemented.

Images