Network element registration method, model request method, network element, and readable storage medium

Abstract

The present application discloses a network element registration method, a model request method, an apparatus, a network element, a communication system and a storage medium. The network element registration method of the embodiments of the present application includes: a first network element sends a network element registration request to a second network element, the network element registration request is used to register information of the first network element in the second network element, and the information of the first network element includes model training related capability information of the first network element, where the model training related capability information of the first network element includes at least one of model platform information supported by the first network element, model description method information supported by the first network element, manufacturer information of the first network element, network element target information with which the first network element can share a model, first indication information for indicating whether the first network element supports model sharing or model interoperation with other network elements, model accuracy information achievable by the first network element, and model training speed information of the first network element.

Description

[Technical Field]

[0001] The present application relates to the field of communication technology, and specifically to a network element registration method, a model request method, an apparatus, a network element, a communication system, and a storage medium. [Background technology]

[0002] With the continuous development of communication technology, network elements can transmit models to each other and use them interchangeably, but during the model transmission process, network elements do not know what platform framework models the other party can receive and use, what platform framework models the other party has, or whether the other party has the platform framework model they need, which results in unnecessary waste of resources such as time, traffic, and communication signals. For example, during the model transmission process, if the model is of a different platform framework, the transmitted model cannot be used, resulting in a relatively low success rate of model transmission. Summary of the Invention [Problem to be solved by the invention]

[0003] The embodiments of the present application provide a network element registration method, a model request method, an apparatus, a network element, a communication system, and a storage medium that can solve the problem of the relatively low success rate of model transmission in the prior art. [Means for solving the problem]

[0004] According to a first aspect, there is provided a network element registration method, the method including: a first network element sending a network element registration request to a second network element, the network element registration request being used to register information of the first network element to the second network element, the information of the first network element including model training related capability information of the first network element, where the model training related capability information of the first network element includes model platform information supported by the first network element, model description method information supported by the first network element, manufacturer information of the first network element; Network element target information of a model in which the first network element can be shared and at least one of first indication information for indicating whether the first network element supports model sharing or model interoperation with other network elements, model accuracy information achievable by the first network element, and model training speed information of the first network element.

[0005] In the embodiments of the present application, the first network element can register the network element information of the first network element with the second network element through a network element registration request, thereby realizing the first network element to be registered with the second network element. Since the network element registration information of the first network element includes model training related capability information, other network elements can search for the first network element that meets the model training needs through the second network element, thereby solving the problem of how the first network element can register its network element information with the second network element and be searched by other network elements.

[0006] According to a second aspect, there is provided a network element registration device for use in a first network element, the network element registration device including: a sending module; the sending module is used to send a network element registration request to a second network element; the network element registration request is used to register information of the first network element in the second network element, the information of the first network element including model training related capability information of the first network element, where the model training related capability information of the first network element includes model platform information supported by the first network element, model description method information supported by the first network element, manufacturer information of the first network element, and Network element target information of a model in which the first network element can be shared and at least one of first indication information for indicating whether the first network element supports model sharing or model interoperation with other network elements, model accuracy information achievable by the first network element, and model training speed information of the first network element.

[0007] According to a third aspect, there is provided a network element registration method, the method including: a second network element receiving a network element registration request sent by a first network element; the network element registration request being used to register information of the first network element to the second network element; the information of the first network element including model training related capability information of the first network element, where the model training related capability information of the first network element includes model platform information supported by the first network element, model description method information supported by the first network element, manufacturer information of the first network element, and Network element target information of a model in which the first network element can be sharedand at least one of first indication information for indicating whether the first network element supports model sharing or model interoperation with other network elements, model accuracy information achievable by the first network element, and model training speed information of the first network element.

[0008] In an embodiment of the present application, the second network element receives a network element registration request sent by the first network element, thereby registering the network element information of the first network element with the second network element, thereby realizing the registration of the first network element with the second network element. Since the network element registration information of the first network element includes model training related capability information, other network elements can search for first network elements that meet the model training needs through the second network element, thereby solving the problem of how the first network element registers network element information with the second network element and can be searched by other network elements.

[0009] According to a fourth aspect, there is provided a network element registration device for use in a second network element, the network element registration device including: a receiving module, the receiving module being used to receive a network element registration request sent by a first network element, the network element registration request being used to register information of the first network element in the second network element, the information of the first network element including model training related capability information of the first network element, where the model training related capability information of the first network element includes model platform information supported by the first network element, model description method information supported by the first network element, manufacturer information of the first network element, and Network element target information of a model in which the first network element can be shared and at least one of first indication information for indicating whether the first network element supports model sharing or model interoperation with other network elements, model accuracy information achievable by the first network element, and model training speed information of the first network element.

[0010] According to a fifth aspect, there is provided a model request method, the method including: a third network element sending a model request message to a first network element; the model request message being used to request acquisition of a model; wherein the model request message includes second information, the second information including at least one of model platform information, model description method information, model accuracy information, manufacturer information of the third network element, and identifier information of the third network element; and the third network element acquiring information of a model matching the second information from the first network element.

[0011] In an embodiment of the present application, the third network element can request the first network element to obtain a model through a model request, and since the model request includes the second information, the third network element can obtain model information that matches the second information from the first network element, thereby improving the success rate of model transmission.

[0012] According to a sixth aspect, there is provided a model request device for use in a third network element, the model request device including: a sending module and an acquiring module. The sending module is used to send a model request message to a first network element, the model request message is used to request acquisition of a model, the model request message includes second information, the second information including at least one of model platform information, model description method information, model accuracy information, manufacturer information of the third network element, and identifier information of the third network element, and the acquiring module is used to acquire information of a model matching the second information from the first network element.

[0013] According to a seventh aspect, there is provided a model request method, the method including: a first network element receiving a model request message sent by a third network element; the model request message being used to request acquisition of a model; wherein the model request message includes second information, the second information including at least one of model platform information, model description method information, model accuracy information, manufacturer information of the third network element, and identifier information of the third network element; and wherein the second information is used by the third network element to acquire information of a model matching the second information from the first network element.

[0014] In an embodiment of the present application, a first network element can receive a model request sent by a third network element, and since the model request includes second information, the third network element can obtain model information matching the second information from the first network element, thereby improving the success rate of model transmission.

[0015] According to an eighth aspect, there is provided a model request device for use in a first network element, the model request device including: a receiving module; the receiving module is used to receive a model request message sent by a third network element, the model request message being used to request acquisition of a model, wherein the model request message includes second information, the second information including at least one of model platform information, model description method information, model accuracy information, manufacturer information of the third network element, and identifier information of the third network element, wherein the second information is used by the third network element to acquire information of a model matching the second information from the first network element.

[0016] According to a ninth aspect, there is provided a network element, the network element including a processor and a memory, the memory storing a program or instructions operable to run on the processor, the program or instructions realizing the steps of the network element registration method according to the first aspect when executed by the processor.

[0017] According to a tenth aspect, there is provided a network element, the network element including: a processor; and a communication interface, wherein the communication interface is used for sending a network element registration request to a second network element, the network element registration request is used for registering information of a first network element with the second network element, the information of the first network element including model training-related capability information of the first network element, wherein the model training-related capability information of the first network element includes at least one of model platform information supported by the first network element, model description method information supported by the first network element, model accuracy information achievable by the first network element, and model training speed information of the first network element.

[0018] According to an eleventh aspect, there is provided a network element, the network element including a processor and a memory, the memory storing a program or instructions operable to run on the processor, the program or instructions realizing the steps of the network element registration method described in the third aspect when executed by the processor.

[0019] According to a twelfth aspect, there is provided a network element, the network element including: a processor; and a communication interface, wherein the communication interface is used to receive a network element registration request sent by a first network element, the network element registration request is used to register information of the first network element with a second network element, the information of the first network element including model training related capability information of the first network element, wherein the model training related capability information of the first network element includes at least one of model platform information supported by the first network element, model description method information supported by the first network element, model accuracy information achievable by the first network element, and model training speed information of the first network element.

[0020] According to a thirteenth aspect, there is provided a network element, the network element including a processor and a memory, the memory storing a program or instructions operable to run on the processor, the program or instructions, when executed by the processor, implementing the steps of the model request method according to the fifth aspect.

[0021] According to a fourteenth aspect, there is provided a network element, the network element including a processor and a communication interface, wherein the communication interface is used to send a model request message to a first network element, the model request message is used to request acquisition of a model, wherein the model request message includes second information, the second information including at least one of model platform information, model description method information, model accuracy information, manufacturer information of the third network element, and identifier information of the third network element, and the third network element acquires information of a model matching the second information from the first network element.

[0022] According to a fifteenth aspect, there is provided a network element, the network element including a processor and a memory, the memory storing a program or instructions operable to run on the processor, the program or instructions implementing the steps of the model request method according to the seventh aspect when executed by the processor.

[0023] According to a sixteenth aspect, there is provided a network element, the network element including: a processor; and a communication interface; wherein the communication interface is used to receive a model request message sent by a third network element, the model request message is used to request acquisition of a model; and wherein the model request message includes second information, the second information including at least one of model platform information, model description method information, model accuracy information, manufacturer information of the third network element, and identifier information of the third network element; and wherein the second information is used by the third network element to acquire information of a model matching the second information from the first network element.

[0024] According to a seventeenth aspect, there is provided a communication system, the communication system including the network element registration device according to the second aspect, e.g., the network element registration device according to the fourth aspect, e.g., the model request device according to the sixth aspect and the model request device according to the eighth aspect, or including the network element according to the ninth, eleventh, thirteenth and fifteenth aspects, or including the network elements according to the tenth, twelfth, fourteenth and sixteenth aspects, wherein the network element may be used to perform steps of the methods according to the first, third, fifth and seventh aspects.

[0025] According to an eighteenth aspect, there is provided a readable storage medium having a program or instructions stored thereon, which, when executed by a processor, performs the steps of the method according to the first aspect, or the steps of the method according to the third aspect, or the steps of the method according to the fifth aspect, or the steps of the method according to the seventh aspect.

[0026] According to a nineteenth aspect, there is provided a chip, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being adapted to run a program or instruction to implement the method according to the first aspect, or to implement the method according to the third aspect, or to implement the method according to the fifth aspect, or to implement the method according to the seventh aspect.

[0027] According to a twentieth aspect, there is provided a computer program / program product, the computer program / program product being stored on a storage medium, the computer program / program product being executed by at least one processor to implement steps of the network element registration method according to the first aspect, or to implement steps of the network element registration method according to the third aspect, or to implement steps of the model request method according to the fifth aspect, or to implement steps of the model request method according to the seventh aspect. [Brief explanation of the drawings]

[0028] [Figure 1] 1 is an architecture schematic diagram of a wireless communication system according to an embodiment of the present application; [Figure 2] FIG. 1 is a schematic diagram of a neural network according to an embodiment of the present application. [Figure 3] FIG. 1 is a schematic diagram of a neuron according to an embodiment of the present application. [Figure 4] 1 is a flowchart of a network element registration method according to an embodiment of the present application; [Figure 5]2 is a second flowchart of a network element registration method according to an embodiment of the present application; [Figure 6] 3 is a third flowchart of a network element registration method according to an embodiment of the present application; [Figure 7] 4 is a fourth flowchart of a network element registration method according to an embodiment of the present application; [Figure 8] 1 is a flowchart of a model request method according to an embodiment of the present application; [Figure 9] 1 is a second flowchart of a model request method according to an embodiment of the present application; [Figure 10] 10 is a third flowchart of a model request method according to an embodiment of the present application. [Figure 11] 2 is a flowchart of a network element registration method and a model request method according to an embodiment of the present application; [Figure 12] 1 is a structural schematic diagram of a network element registration device according to an embodiment of the present application; [Figure 13] 2 is a second structural schematic diagram of a network element registration device according to an embodiment of the present application; [Figure 14] 1 is a structural schematic diagram of a model request device according to an embodiment of the present application; [Figure 15] 2 is a second structural schematic diagram of a model request device according to an embodiment of the present application; [Figure 16] 1 is a hardware structure schematic diagram of a communication device according to an embodiment of the present application; [Figure 17] FIG. 2 is a hardware structure schematic diagram of a network element according to an embodiment of the present application; DETAILED DESCRIPTION OF THE INVENTION

[0029] The following clearly describes the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present application fall within the scope of protection of the present application.

[0030] The terms "first," "second," etc. in the specification and claims of this application are intended to distinguish between similar objects and are not intended to describe a particular order or sequence. It should be understood that terms used in this manner are interchangeable where appropriate, so that embodiments of this application may be performed in orders other than those illustrated or described herein, and that objects distinguished by "first" and "second" are generally of the same type and do not limit the number of objects; for example, a first object may be one or more. Furthermore, "and / or" in the specification and claims indicates at least one of the connected objects, and the character " / " generally indicates an "or" relationship between the related objects.

[0031] It should be noted that the techniques described in the embodiments of the present application are not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be applied to other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-Carrier Frequency Division Multiple Access (SC-FDMA), and other systems. The terms "system" and "network" in the embodiments of the present application are always used interchangeably, and the described techniques may be used in the above-mentioned systems and radio technologies as well as other systems and radio technologies. Although the following description describes a New Radio (NR) system for illustrative purposes and uses NR terminology in most of the following description, these techniques may be applied to applications other than NR system applications, such as 6th Generation (6G) communication systems.

[0032] 1 is a block diagram of a wireless communication system to which the embodiment of the present application can be applied. The wireless communication system includes a terminal 11 and a network side device 12. Here, the terminal 11 may be a terminal-side device such as a mobile phone, a tablet personal computer, a laptop computer (also called a notebook computer), a personal digital assistant (PDA), a palmtop computer, a netbook, an ultra-mobile personal computer (UMPC), a mobile internet device (MID), an augmented reality (AR) / virtual reality (VR) device, a robot, a wearable device, a vehicle-mounted equipment (VUE), a pedestrian-mounted equipment (PUE), a smart home (home equipment with wireless communication capabilities, such as a refrigerator, television, washing machine, or furniture), a game console, a personal computer (PC), a teller machine, or a self-service machine, and wearable devices include a smart watch, a smart wristband, a smart earphone, a smart glasses, a smart accessory (a smart bracelet, a smart hand chain, a smart ring, a smart necklace, a smart ankle bracelet, a smart anklet, etc.), a smart band, a smart garment, etc. It should be noted that the terminal 11 in the embodiment of the present application is not limited to a specific type. The network side equipment 12 may include access network equipment or core network equipment, where the access network equipment 12 may be called radio access network equipment, radio access network (RAN), radio access network function or radio access network unit.The access network equipment 12 may include a base station, a WLAN access point, a WiFi node, or the like. The base station may be called a Node B, an evolved Node B (eNB), an access point, a base transceiver station (BTS), a radio base station, a radio transceiver, a basic service set (BSS), an extended service set (ESS), a home B node, a home evolved B node, a transmitting receiving point (TRP), or any other suitable term in the art. As long as the same technical effect is achieved, the base station is not limited to a specific technical term. It should be noted that the embodiments of this application only take the base station in an NR system as an example, and do not limit the specific type of base station. Core network devices include core network nodes, core network functions, mobility management entities (MMEs), access and mobility management functions (AMFs), session management functions (SMFs), user plane functions (UPFs), and policy control functions (PCFs). Function (PCF), Policy and Charging Rules Function (PCRF), Edge Application Server Discovery Function (EASDF), Unified Data Management (UDM), Unified Data Repository (UDR), Home Subscriber Server (HSS), Centralized Network Configuration (CNS) The core network function may include, but is not limited to, at least one of a network configuration function (CNC), a network repository function (NRF), a network exposure function (NEF), a local NEF (Local NEF or L-NEF), a binding support function (BSF), an application function (AF), etc. It should be noted that the embodiments of the present application only take core network devices in an NR system as examples, and do not limit the specific type of core network device.

[0033] The following provides an explanation and description of some concepts and / or terms related to the network element registration method, model request method, device, network element, communication system, and storage medium according to the embodiments of the present application.

[0034] 1. Artificial Intelligence (AI) and AI models: Artificial intelligence (AI) is now widely applied in various fields. AI models have various algorithm implementation methods, such as neural networks, decision trees, support vector machines, Bayesian classifiers, etc. This application uses neural networks as an example for explanation, but does not limit the specific type of AI module.

[0035] As shown in Figure 2, it is a schematic diagram of one neural network. X1, X2...Xn etc. are input values, Y is the output result, and each JPEG2023185826000001.jpg55 indicates that each neuron is a place where an operation is performed, and the result is then passed to the next layer. The input layer, hidden layer, and output layer, which are made up of these many neurons, make up a neural network. The number of hidden layers and the number of neurons in each layer are the "network structure" of the neural network.

[0036] Here, a neural network consists of neurons, and Figure 3 shows a schematic diagram of a neuron. Here, a1, a2, ... aK (i.e., X1 ... Xn above) are inputs, w is a weight (multiplication coefficient), b is a bias (addition coefficient), σ(z) is an activation function, and z is an output value. Common activation functions include sigmoid, tanh, ReLU (Rectified Linear Unit), etc. The parameter information of each neuron, combined with the algorithm used, constitutes the "parameter information" of the entire network and is also an important part of the AI ​​model file.

[0037] In actual use, an AI model is a file containing elements such as network structure and parameter information. The trained AI model can be directly reused by the framework platform to directly perform intelligent functions such as judgment and identification without repeated construction or learning.

[0038] 2. Network framework Neural networks have various implementation frameworks, including TensorFlow, PyTorch, Keras, MXNet, and Caffe2, and each framework has a different focus. For example, Caffe2 and Keras are upper-level deep learning frameworks that can quickly verify models, while TensorFlow and PyTorch are lower-level deep learning frameworks that can realize detailed modifications to the lower layers of neural networks.

[0039] For example, PyTorch focuses on supporting dynamic graph models, TensorFlow focuses on supporting various hardware and has fast operation speed, and Caffe2 is lightweight. Each implementation framework uses its own method to describe neural networks and complete operations such as network construction, training, and inference. Generally, the model description methods in different implementation frameworks are not understood by other frameworks, so models between them cannot be used interchangeably.

[0040] 3. Network Data Analytics Function (NWDAF) The network element can be decomposed into two parts: NWDAF (AnLF) and NWDAF (MTLF). The former is the network element responsible for the inference function (Analytics Logical Function, AnLF), and the latter is the network element responsible for the training function (Model Training Logical Function, MTLF).

[0041] The following describes in detail the network element registration method and model request method according to the embodiments of the present application through several embodiments and application scenarios in conjunction with the drawings.

[0042] Currently, AI platform frameworks are independent of each other, and only a few models can be converted between them. These models are not interoperable, making it impossible to use them with other frameworks, posing significant obstacles to practical use. Because each framework's focus and, consequently, its supported development languages, are different, two nodes using different frameworks cannot transfer AI model information. Two nodes using different frameworks have different network description methods, data compression methods, and file storage formats, making it impossible to analyze networks trained with other frameworks. Similarly, different developers define and write frameworks differently, creating relatively high barriers to conversion and making them difficult to convert. Even within the same framework, different file storage formats can vary depending on information such as different versions, which can result in inconsistent analysis results or even failure to analyze when nodes using different framework versions transfer an AI model.

[0043] In the current protocol standard, only the needs for network element registration and discovery, including network element identifier information, service and some capability information (NWDAF Capabilities, Analytics aggregation capability, Analytics metadata provisioning capability), are specified, but the necessary information regarding model transmission is not included in the standard registration and discovery flow.

[0044] In an embodiment of the present application, information regarding model propagation is added in the smart network element registration and discovery process, and during registration, information regarding the model platform / framework it uses is also registered, and when a network element is discovered, such messages can be filtered to select an appropriate network element.

[0045] Specifically, as a solution, an MTLF network element can register its network element information with an NRF network element through a network element registration request, thereby realizing the registration of the MTLF network element with the NRF network element. Since the network element registration information of the MTLF network element includes model training related capability information, other network elements can search for MTLF network elements that meet their model training needs through the NRF network element, thereby solving the problem of how an MTLF network element can register its network element information with an NRF network element and be searched by other network elements.

[0046] As another solution, the NRF network element can receive a network element registration request sent by the MTLF network element and register the network element information of the MTLF network element with the NRF network element, thereby realizing the registration of the MTLF network element with the NRF network element. Since the network element registration information of the MTLF network element includes model training related capability information, other network elements can search for MTLF network elements that meet the model training needs through the NRF network element, thereby solving the problem of how the MTLF network element registers its network element information with the NRF network element and can be searched by other network elements.

[0047] In another method, the AnLF network element may request the MTLF network element to obtain a model through a model request, and since the model request includes second information, the AnLF network element can obtain model information that matches the second information from the MTLF network element, thereby improving the success rate of model transmission.

[0048] As another solution, the MTLF network element may receive a model request sent by an AnLF network element, and the model request includes second information, so that the AnLF network element can obtain model information matching the second information from the MTLF network element, thereby improving the success rate of model transmission.

[0049] An embodiment of the present application provides a network element registration method, and Figure 4 shows a flowchart of the network element registration method according to the embodiment of the present application. As shown in Figure 4, the network element registration method according to the embodiment of the present application may include the following steps 201 and 202:

[0050] Step 201: A first network element sends a network element registration request to a second network element.

[0051] In an embodiment of the present application, the network element registration request is used to register information of a first network element to a second network element, and the information of the first network element includes model training related capability information of the first network element.

[0052] Step 202: The second network element receives a network element registration request sent by the first network element.

[0053] In an embodiment of the present application, the model training related capability information of the first network element is: Model platform information supported by the first network element; Model description method information supported by the first network element; Manufacturer information of the first network element; Network element target information of a model in which the first network element can be shared and, First indication information for indicating whether the first network element supports model sharing or model interoperation with other network elements; model accuracy information achievable by the first network element; and model training rate information of the first network element.

[0054] Optionally, in the embodiment of the present application, the first network element is a model training network element, which may be a MTLF network element, an NWDAF network element, or an NWDAF containing MTLF network element.

[0055] Optionally, in an embodiment of the present application, the second network element is a network element responsible for capability storage, which may be an NRF network element, a UDM network element, or a Data Collection Application Function (DCAF) network element.

[0056] Optionally, in an embodiment of the present application, the first network element may send a Nnrf_NFManagement_NFRegister Register network element registration request to the second network element to request that the information of the first network element be registered in the second network element.

[0057] In an embodiment of the present application, the model platform information supported by the first network element is used to indicate the platforms that this network element can understand and use, such as TensorFlow, PyTorch, etc.

[0058] Optionally, in the embodiment of the present application, the first network element may be based on the model platform training model, or the model may be obtained based on the model platform training.

[0059] Optionally, in the embodiment of the present application, the model platform information supported by the first network element includes name or address information of one or more model platforms.

[0060] In the embodiment of the present application, the model platform information is used to instruct the first network element to train and generate a model based on the model platform corresponding to the name or address information of the model platform.

[0061] In the embodiment of the present application, the model description method information supported by the first network element is used to instruct this network element to describe the method technology used by the model.

[0062] Optionally, in the embodiment of the present application, the model description method information supported by the first network element is one of model format information and model language information.

[0063] Optionally, in the embodiment of the present application, the model language information may be Open Neural Network Exchange (ONNX) language.

[0064] Optionally, in an embodiment of the present application, the first network element supports expressing the trained model in model format information or model language information.

[0065] Optionally, in an embodiment of the present application, the model accuracy information achievable by the first network element is used to instruct the first network element to describe the degree of accuracy of identification or decision-making that can be achieved after training the model.

[0066] In the embodiments of the present application, model accuracy is used to indicate the degree of accuracy of the model's output results.

[0067] In an embodiment of the present application, the model accuracy information may be the number of times the model decision result is correct divided by the total number of decisions, that is, model accuracy=number of correct results / total number.

[0068] Optionally, in the embodiment of the present application, the model accuracy information may be identified in the form of a decimal, a percentage, or high, medium, or low.

[0069] Optionally, in the embodiments of the present application, the model training speed information of the first network element may be the time required for the first network element to obtain a model with a certain accuracy through training. For example, if the first network element trains one type of model and requires 2 hours to achieve 90% accuracy, this time represents the model training speed information of the first network element.

[0070] Optionally, in an embodiment of the present application, the first indication information indicating that the first network element supports model sharing or model interoperation with other network elements may be understood to mean that the first network element has the capability of model sharing or model interoperation with other network elements.

[0071] Optionally, in an embodiment of the present application, the information of the first network element is: Algorithm information used when the first network element trains the model and, Manufacturer information of the first network element; Network element target information of a model in which the first network element can be shared and, Limitation condition information for the first network element to share the model; network element information storing a model trained by the first network element; and

[0072] Optionally, in the embodiments of the present application, Algorithm information used when the first network element trains the model may be an algorithm type related to AI such as machine learning that the first network element supports when training a model, such as deep learning, linear regression, gradient descent, etc., and this algorithm information can provide the model supported by this first network element.

[0073] Optionally, in the embodiment of the present application, the manufacturer information of the first network element is used to indicate the manufacturer information to which this network element belongs.

[0074] In the examples of the present application, Network element target information of a model in which the first network element can be shared is used to indicate the network element target information limited by this network element itself when sharing or transmitting a model.

[0075] Optionally, in the embodiments of the present application, Network element target information of a model in which the first network element can be shared includes at least one of information of one or more model inference function network elements and information of one or more model training function network elements.

[0076] Optionally, in the embodiment of the present application, the above network element object information is description information or identifier information of the network element object.

[0077] Optionally, in an embodiment of the present application, the restriction condition information under which the first network element shares the model includes at least one of time restriction condition information and area restriction condition information.

[0078] In an embodiment of the present application, the above-mentioned time restriction condition information is used to indicate the time during which the first network element allows model sharing, for example, from 7 p.m. to 6 a.m. the next day, and the area restriction condition information is used to indicate the area during which the first network element allows model sharing, for example, the location of the network element that shares the model with the first network element should be within this area restriction information, for example, "Suzhou."

[0079] In the examples of the present application, network element information storing a model trained by the first network element; teeth, used to indicate a network element that stores a model trained by the first network element. .

[0080] Optionally, in the embodiments of the present application, network element information storing a model trained by the first network element; may be identifier information of the network element responsible for storing the model information, for example, the network element responsible for storing the model (Analytics Data Repository Function, ADRF), network element type information, etc.

[0081] Optionally, in an embodiment of the present application, the information of the first network element further includes at least one of version information of the first network element, type information of the first network element, identifier information of the first network element, and data analysis identifier information supported by the first network element.

[0082] In the embodiment of the present application, the version information of the first network element is used to indicate the version information of the model used by this network element.

[0083] In an embodiment of the present application, the type information of the first network element is used to indicate what type of network element is currently registered. For example, if the type information of the first network element is an NWDAF network element type, it indicates that the currently registered network element is an NWDAF network element.

[0084] Optionally, in the embodiment of the present application, the identifier information of the first network element may be any one of Fully Qualified Domain Name (FQDN) information and IP address information.

[0085] In an embodiment of the present application, the full qualified domain name information is used to indicate the location of the first network element and the connectivity of the first network element.

[0086] In an embodiment of the present application, the data analysis identifier information supported by the first network element is used to indicate the task type that this network element can perform.

[0087] Optionally, in an embodiment of the present application, the information of the first network element further includes at least one of information on the type of training supported by the first network element, information on the time when the first network element supports federated learning training, and metadata information possessed by the first network element.

[0088] In an embodiment of the present application, the training type information supported by the first network element is used to indicate the AI ​​model training algorithm type supported by the first network element.

[0089] Optionally, in an embodiment of the present application, the type information of training supported by the first network element includes indication information of whether the first network element supports federated learning training, and at least one of a horizontal federated learning training type, a vertical federated learning training type, deep learning, linear regression, and gradient descent.

[0090] In an embodiment of the present application, the time information that the first network element supports federated learning training is used to indicate the time to perform the federated learning training supported by the first network element, and performing the federated learning training within this time period, for example, from 10 p.m. to 6 a.m. the next morning, will result in relatively good performance.

[0091] In an embodiment of the present application, the metadata information possessed by the first network element is used to indicate the data information that the first network element can cover, obtain, and provide.

[0092] Optionally, in an embodiment of the present application, the metadata information possessed by the first network element includes at least one of an input data type, an output data type, a data amount, and a data range.

[0093] In the embodiment of the present application, the input data type is the input data type of the associative learning training, and the output data type is the output data type of the associative learning training.

[0094] In the embodiment of the present application, the data type refers to whether or not there is a clear characteristic in the data within the area, for example, the data is concentrated in the morning and dispersed in the evening.

[0095] In the embodiment of the present application, the data range is the service range of the first network element.

[0096] Optionally, in an embodiment of the present application, the data range includes at least one of the service area of ​​the first network element, the area from which the first network element can collect data, and the object from which the first network element can collect data.

[0097] Optionally, in an embodiment of the present application, the collectable data of the first network element includes metadata information and training data for model training.

[0098] Optionally, in an embodiment of the present application, the area in which the first network element can collect data may be any one of the first network element service area, a sub-area range under the first network element service area, and a target of finer collectable data granularity (e.g., one UE list).

[0099] Optionally, the embodiment of the present application further includes the following steps 203 and 204 after the above step 202.

[0100] Step 203: The second network element sends a registration response to the first network element.

[0101] In the embodiment of the present application, the registration response is used to indicate successful registration of the first network element.

[0102] Step 204, the first network element receives the registration response sent by the second network element.

[0103] Optionally, in an embodiment of the present application, the second network element may send a registration response Nnrf_NFManagement_NFRegister response to the first network element to notify that the first network element has been successfully registered.

[0104] An embodiment of the present application further provides a network element registration method, in which a first network element can register its network element information with a second network element through a network element registration request, thereby realizing the first network element to be registered with the second network element. Since the network element registration information of the first network element includes model training related capability information, other network elements can search for first network elements that meet the model training needs through the second network element, thereby solving the problem of how the first network element can register its network element information with the second network element and be searched by other network elements.

[0105] Optionally, in an embodiment of the present application, as shown in FIG. 5 in combination with FIG. 4, after the above step 202, the network element registration method according to the embodiment of the present application further includes the following steps 205 and 206.

[0106] Step 205: The third network element sends a search request to the second network element.

[0107] In an embodiment of the present application, the search request is used to request a search for a target network element, and the search request includes at least one of model training related capability information required by the third network element and the first information.

[0108] Step 206: The second network element receives the search request sent by the third network element.

[0109] In an embodiment of the present application, the model training related capability information required by the third network element includes at least one of: model platform information supported by the target network element required by the third network element; model description method information supported by the target network element required by the third network element; model accuracy information achieved by the target network element required by the third network element; and model training speed information of the target network element required by the third network element.

[0110] Optionally, in the embodiments of the present application, the third network element may be an AnLF network element, an NWDAF network element, or an NWDAF containing AnLF network element.

[0111] Optionally, in the embodiment of the present application, the third network element may send a Nnrf_NFDiscovery_Request search request to the second network element to request the second network element to feedback network element information that meets the conditions.

[0112] In an embodiment of the present application, the model platform information supported by the target network element required by the third network element is used to indicate a platform that the required target network element can understand and use, such as TensorFlow, PyTorch, etc.

[0113] Optionally, in the embodiment of the present application, the target network element may be based on the model platform training model, or the model may be obtained based on the model platform training.

[0114] Optionally, in the embodiment of the present application, the model platform information supported by the target network element includes name or address information of one or more model platforms.

[0115] In the embodiment of the present application, the model platform information is used to instruct the target network element to train and generate a model based on the model platform corresponding to the name or address information of the model platform.

[0116] In the embodiment of the present application, the model description method information supported by the target network element required by the third network element is used to indicate the method technology used by the required target network element description model.

[0117] Optionally, in an embodiment of the present application, the model accuracy information achieved by the target network element required by the third network element is used to instruct the required target network element to describe the degree of accuracy of identification or decision-making that can be achieved after training the model.

[0118] In the embodiments of the present application, model accuracy is used to indicate the degree of accuracy of the model's output results.

[0119] Optionally, in an embodiment of the present application, the model training speed information of the target network element required by the third network element may be the time required for the required target network element to undergo training and obtain a model of a certain accuracy.

[0120] Optionally, in an embodiment of the present application, the search request further includes data analysis identifier information of the target network element required by the third network element.

[0121] Optionally, in the embodiment of the present application, the data analysis identifier information of the target network element required by the third network element is used to indicate the task type that the required target network element can support.

[0122] Optionally, in an embodiment of the present application, as shown in FIG. 6 in combination with FIG. 5, after the above step 206, the network element registration method according to the embodiment of the present application further includes the following step 207:

[0123] Step 207: The second network element determines a target network element based on the search request.

[0124] Optionally, the model training related capability information of the target network element matches the model training related capability information required by a third network element.

[0125] As can be seen, the second network element determines a network element whose model training related capability information matches the model training related capability information required by the third network element as a target network element.

[0126] Alternatively, if the query request includes model training related capability information required by a third network element, the above step 207 may be specifically implemented by at least one of the following steps 207a to 207d.

[0127] In step 207a, the second network element determines a target network element based on model platform information supported by the target network element required by the third network element.

[0128] In an embodiment of the present application, the target network element supports the model platform information required by the third network element.

[0129] As can be seen, the second network element determines the network element that supports the model platform information required by the third network element as the target network element.

[0130] Step 207b: the second network element determines the target network element based on the model description method information supported by the target network element required by the third network element.

[0131] In the embodiment of the present application, the target network element supports the model description method information required by the third network element.

[0132] As can be seen, the second network element determines the network element that supports the model description method information required by the third network element as the target network element.

[0133] In step 207c, the second network element determines the target network element based on the model accuracy information achieved by the target network element required by the third network element.

[0134] In an embodiment of the present application, the target network element supports the model accuracy information to be achieved required by a third network element.

[0135] As can be seen, the second network element determines as the target network element the network element that supports the model accuracy information that the third network element desires to achieve.

[0136] Step 207d: the second network element determines the target network element based on the model training speed information of the target network element required by the third network element.

[0137] In an embodiment of the present application, the target network element supports model training rate information required by a third network element.

[0138] As can be seen, the second network element determines as the target network element the network element that supports the model training rate information required by the third network element.

[0139] Optionally, in an embodiment of the present application, the first information includes at least one of algorithm information used in the target network element training model required by the third network element, manufacturer information of the target network element required by the third network element, restriction condition information under which the target network element required by the third network element shares the model, identifier information of the third network element, and instruction information shared by the model.

[0140] Optionally, in an embodiment of the present application, the algorithm information used for the target network element training model required by the third network element may be an algorithm type related to AI such as machine learning that the target network element supports when training the model, such as deep learning, linear regression, gradient descent, etc., and this algorithm information can be used to obtain the model supported by the first network element.

[0141] Optionally, in the embodiment of the present application, the manufacturer information of the target network element required by the third network element is used to indicate the manufacturer information of the required target network element.

[0142] Optionally, in an embodiment of the present application, the restriction condition information for the target network element required by the third network element to share the model includes at least one of time information supported by the target network element and area restriction information of the target network element.

[0143] In an embodiment of the present application, the time information supported by the target network element demanded by the third network element is used to indicate the time during which the demanding target network element will allow model sharing, and the area restriction information of the target network element demanded by the third network element is used to indicate the area during which the demanding target network element will allow model sharing.

[0144] Optionally, in an embodiment of the present application, the model-shared indication information is used to indicate that the network element required by the third network element is a network element that supports model sharing or model interoperation with other network elements.

[0145] Optionally, the second network element may determine the target network element based on the first information in the search request.

[0146] Optionally, in the embodiment of the present application, when the search request includes first information, the above step 207 may be specifically realized by at least one of the following steps 207e to 207i.

[0147] Step 207e: The second network element determines a target network element based on the algorithm information used in the target network element training model required by the third network element.

[0148] In an embodiment of the present application, the target network element supports the algorithm information used in the training model required by the third network element.

[0149] As can be seen, the second network element determines as the target network element the network element that supports the algorithm information used in the training model required by the third network element.

[0150] Step 207f: the second network element determines the target network element based on the manufacturer information of the target network element required by the third network element.

[0151] In the embodiment of the present application, the target network element supports the manufacturer information required by the third network element.

[0152] As can be seen, the second network element determines the network element that supports the manufacturer information required by the third network element as the target network element.

[0153] In step 207g, the second network element determines a target network element based on the restriction condition information that the target network element required by the third network element shares the model.

[0154] Step 207h: The second network element determines a target network element based on the identifier information of the third network element, wherein the target information of the network element with which the target network element can share the model matches the identifier information of the third network element; understandably, the target information of the network element with which the target network element can share the model matching the identifier information of the third network element may indicate that the target information of the network element with which the target network element can share the model includes the identifier information of the third network element.

[0155] In step 207i, the second network element determines a target network element based on the indication information shared by the model, where the target network element supports model sharing or model interoperation with other network elements.

[0156] In an embodiment of the present application, the target network element supports constraint information for sharing the model required by a third network element.

[0157] As can be seen, the second network element determines as the target network element the network element that supports the constraint information that shares the model required by the third network element.

[0158] Optionally, in an embodiment of the present application, as shown in FIG. 7 in combination with FIG. 6, after the above step 207, the network element registration method according to the embodiment of the present application further includes the following steps 208 and 209.

[0159] Step 208: The second network element sends a search response to the third network element.

[0160] In an embodiment of the present application, the search response includes target information.

[0161] Step 209: The third network element receives the search response sent by the second network element.

[0162] In an embodiment of the present application, the target information includes at least one of identifier information of the target network element, address information of the target network element, model platform information supported by the target network element, model description method information supported by the target network element, model accuracy information achievable by the target network element, model training speed information of the target network element, algorithm information used in the target network element training model, manufacturer information of the target network element, restriction condition information under which the target network element shares the model, and network element information of the target network element stored training model.

[0163] Optionally, in an embodiment of the present application, the target information further includes at least one of a query validity period and version information of the target network element.

[0164] It should be noted that the information about the target network element can be found in the above embodiment and will not be further described here.

[0165] An embodiment of the present application provides a network element registration method, in which a second network element can receive a search request sent by a third network element, determine a target network element based on the search request, and send a search response to the third network element to allow the third network element to determine the target network element, thereby subsequently requesting the target network element to obtain a model.

[0166] It should be mentioned that in the network element registration method according to the embodiment of the present application, the execution body may be a network element registration device or a control module for executing the network element registration method in the network element registration device.

[0167] An embodiment of the present application provides a model request method, and Fig. 8 shows a flowchart of the model request method according to the embodiment of the present application. As shown in Fig. 8, the model request method according to the embodiment of the present application may include the following steps 301 to 303.

[0168] Step 301: A third network element sends a model request message to a first network element.

[0169] In the embodiment of the present application, the model request message is used to request acquisition of a model.

[0170] Step 302: A first network element receives a model request message sent by a third network element.

[0171] In an embodiment of the present application, the model request message includes second information, which includes at least one of model platform information, model description method information, model accuracy information, manufacturer information of the third network element, and identifier information of the third network element.

[0172] In an embodiment of the present application, the second information is used by the third network element to obtain model information matching the second information from the first network element.

[0173] Optionally, in the embodiment of the present application, the first network element is a model training network element, which may be a MTLF network element, an NWDAF network element, or an NWDAF containing MTLF network element.

[0174] Optionally, in the embodiments of the present application, the third network element may be an AnLF network element, an NWDAF network element, or an NWDAF containing AnLF network element.

[0175] Optionally, in an embodiment of the present application, the third network element may send a model request Nnwdaf_MLModelInfo_Request to the first network element to request acquisition of the model.

[0176] Optionally, in an embodiment of the present application, the model platform information is used to indicate a platform that the demanding network element can understand and use, such as TensorFlow, PyTorch, etc.

[0177] Optionally, in the embodiment of the present application, the first network element may be based on the model platform training model, or the model may be obtained based on the model platform training.

[0178] Optionally, in the embodiment of the present application, the model platform information supported by the first network element includes name or address information of one or more model platforms.

[0179] In the embodiment of the present application, the model platform information is used to instruct the first network element to train and generate a model based on the model platform corresponding to the name or address information of the model platform.

[0180] In the embodiment of the present application, the model description method information is used to indicate the method technology used by the desired network element description model.

[0181] Optionally, in the embodiment of the present application, the model description method information is one of model format information and model language information.

[0182] In the embodiment of the present application, the model description method information is used to instruct the first network element to feed back the model to the third network element in the form of model format information or model language information.

[0183] Optionally, in the embodiment of the present application, the model language information may be ONNX (One Universal Model Description Language) language.

[0184] In an embodiment of the present application, the model accuracy information is used to instruct the desired network element to describe the degree of accuracy of discrimination or decision making that can be achieved after training the model.

[0185] In the embodiments of the present application, model accuracy is used to indicate the degree of accuracy of the model's output results.

[0186] In an embodiment of the present application, the model accuracy information may be the number of times the model decision result is correct divided by the total number of decisions, that is, model accuracy=number of correct results / total number.

[0187] Optionally, in the embodiment of the present application, the model accuracy information may be identified in the form of a decimal, a percentage, or high, medium, or low.

[0188] In an embodiment of the present application, the model request method further includes: the first network element obtaining, based on the second information, information of a model matching the second information.

[0189] Optionally, the first network element obtaining, based on the second information, information of a model matching the second information, The first network element acquires a target model based on model platform information included in the second information, and the target model is generated based on a model platform corresponding to the model platform information; The first network element acquires a target model based on model description method information included in the second information, and the target model is represented based on model language information or model format information corresponding to the model description method information.

[0190] The first network element obtains a target model based on the model accuracy information included in the second information, and the model accuracy of the target model matches the model accuracy information. Optionally, the model accuracy of the target model matching the model accuracy information may refer to the model accuracy of the target model being the same as the model accuracy indicated by the model accuracy information, or the model accuracy of the target model being within the model accuracy range indicated by the model accuracy information, or the model accuracy of the target model being greater than the model accuracy indicated by the model accuracy information, and this embodiment is not specifically limited. In an embodiment of the present application, the first network element may determine that the first network element allows model sharing or model interoperation with the third network element based on the manufacturer information of the third network element included in the second information, where the first network element allowing model sharing or model interoperation with the third network element may be understood as the manufacturer information of the third network element being within the manufacturer information range for which the first network element allows model sharing or model interoperation.

[0191] Or, In an embodiment of the present application, the first network element determines that the first network element allows model sharing or model interoperation with the third network element based on the identifier information of the third network element included in the second information, where the first network element allows model sharing or model interoperation with the third network element may be understood as the third network element being within a target range of shareable network elements.

[0192] An embodiment of the present application provides a model request method, in which a third network element can request a first network element to obtain a model through a model request, and since the model request includes second information, the third network element can obtain model information matching the second information from the first network element, thereby improving the success rate of model transmission.

[0193] Step 303: The third network element obtains information of a model that matches the second information from the first network element.

[0194] Optionally, in an embodiment of the present application, the information of the model includes at least one of file information of the model and download address information of the model file.

[0195] Optionally, in the embodiment of the present application, the file information of the model may include elements such as complete network structure and parameter information to generate a model corresponding to the target task.

[0196] Optionally, in an embodiment of the present application, the second information is: Information about the algorithm used to train the model; and Model version information, and feedback time information of the model.

[0197] In an embodiment of the present application, the algorithm information used in the training model is used to indicate the type of AI-related algorithm, such as machine learning, that the demanding network element supports when training the model, and this algorithm information can be used to obtain the model supported by the network element.

[0198] In the embodiment of the present application, the model version information is used to indicate the model version information used by the requesting network element.

[0199] In the embodiment of the present application, the model feedback time information is used to indicate the feedback time of the required network element training model, such as the time required for model training or the deadline for model feedback.

[0200] In an embodiment of the present application, the first network element obtaining model information matching the second information based on the second information includes: the first network element obtaining a target model based on algorithm information used in the training model, and the algorithm type used by the target model is the same as the algorithm type indicated by the algorithm information used in the training model; The first network element obtains a target model according to the version information of the model, and the version information of the target model is the same as the version information of the model; The first network element may obtain a target model based on the feedback time information of the model, wherein the feedback time of the target model matches the feedback time indicated by the feedback time information of the model, for example, a time taken for model training of the target model is less than a time taken for model training indicated by the feedback time information of the model.

[0201] Optionally, in an embodiment of the present application, the second information further includes at least one of data analysis identifier information and model limiting condition information.

[0202] Optionally, in an embodiment of the present application, the data analysis identifier information is used to indicate the type of task the requesting network element is to perform.

[0203] Optionally, in an embodiment of the present application, the model limiting condition information includes at least one of time limiting condition information and area limiting condition information.

[0204] In an embodiment of the present application, the above-mentioned time restriction condition information is used to indicate the time during which the demanding network element allows model sharing, for example, from 7 p.m. to 6 a.m. the next day, and the area restriction condition information is used to indicate the area during which the demanding network element allows model sharing, for example, the location of the network element that will share the model with the first network element should be within this area restriction information, for example, "Suzhou."

[0205] An embodiment of the present application provides a model request method, in which a third network element can request a first network element to obtain a model through a model request, and since the model request includes second information, the third network element can obtain model information matching the second information from the first network element, thereby improving the success rate of model transmission.

[0206] Optionally, in an embodiment of the present application, as shown in FIG. 9 in combination with FIG. 8, before the above step 301, the model request method according to the embodiment of the present application further includes the following steps 304 and 305.

[0207] Step 304: The third network element sends a search request to the second network element.

[0208] In an embodiment of the present application, the search request is used to request a search for a target network element, and the search request includes at least one of model training related capability information required by the third network element and the first information.

[0209] Step 305: The second network element receives the search request sent by the third network element.

[0210] In an embodiment of the present application, the model training related capability information required by the third network element includes at least one of: model platform information supported by the target network element required by the third network element; model description method information supported by the target network element required by the third network element; model accuracy information achieved by the target network element required by the third network element; and model training speed information of the target network element required by the third network element.

[0211] Optionally, in the embodiment of the present application, the third network element may send a Nnrf_NFDiscovery_Request search request to the second network element to request the second network element to feedback network element information that meets the conditions.

[0212] In an embodiment of the present application, the model platform information supported by the target network element required by the third network element is used to indicate a platform that the required target network element can understand and use, such as TensorFlow, PyTorch, etc.

[0213] In the embodiment of the present application, the model description method information supported by the target network element required by the third network element is used to indicate the method technology used by the required target network element description model.

[0214] Optionally, in the embodiment of the present application, the model platform information supported by the target network element includes name or address information of one or more model platforms.

[0215] In the embodiment of the present application, the model platform information is used to instruct the target network element to train and generate a model based on the model platform corresponding to the name or address information of the model platform.

[0216] Optionally, in an embodiment of the present application, the model accuracy information achieved by the target network element required by the third network element is used to instruct the required target network element to describe the degree of accuracy of identification or decision-making that can be achieved after training the model.

[0217] Optionally, in an embodiment of the present application, the model training speed information of the target network element required by the third network element may be the time required for the required target network element to undergo training and obtain a model of a certain accuracy.

[0218] Optionally, in an embodiment of the present application, the search request further includes data analysis identifier information of the target network element required by the third network element.

[0219] Optionally, in the embodiment of the present application, the data analysis identifier information of the target network element required by the third network element is used to indicate the task type that the required target network element can support.

[0220] Optionally, in an embodiment of the present application, the first information includes at least one of algorithm information used in the target network element training model required by the third network element, manufacturer information of the target network element required by the third network element, restriction condition information under which the target network element required by the third network element shares the model, identifier information of the third network element, and instruction information shared by the model.

[0221] Optionally, in an embodiment of the present application, the algorithm information used for the target network element training model required by the third network element may be an algorithm type related to AI such as machine learning that the target network element supports when training the model, such as deep learning, linear regression, gradient descent, etc., and this algorithm information can be used to obtain the model supported by the target network element.

[0222] Optionally, in the embodiment of the present application, the manufacturer information of the target network element required by the third network element is used to indicate the manufacturer information of the required target network element.

[0223] Optionally, in an embodiment of the present application, the restriction condition information for the target network element required by the third network element to share the model includes at least one of time information supported by the target network element and area restriction information of the target network element.

[0224] In an embodiment of the present application, the time information supported by the target network element demanded by the third network element is used to indicate the time during which the demanding target network element will allow model sharing, and the area restriction information of the target network element demanded by the third network element is used to indicate the area during which the demanding target network element will allow model sharing.

[0225] Optionally, in an embodiment of the present application, the model-shared indication information is used to indicate that the network element required by the third network element is a network element that supports model sharing or model interoperation with other network elements.

[0226] Optionally, in an embodiment of the present application, as shown in FIG. 10 in combination with FIG. 9, after the above step 305, the model request method according to the embodiment of the present application further includes the following steps 306 and 307:

[0227] Step 306: The second network element sends a search response to the third network element.

[0228] In an embodiment of the present application, the search response includes target information.

[0229] Step 307: the third network element receives the search response sent by the second network element.

[0230] In an embodiment of the present application, the target information includes at least one of identifier information of the target network element, address information of the target network element, model platform information supported by the target network element, model description method information supported by the target network element, model accuracy information achievable by the target network element, model training speed information of the target network element, algorithm information used in the target network element training model, manufacturer information of the target network element, restriction condition information under which the target network element shares the model, and network element information of the target network element stored training model.

[0231] Optionally, in the embodiment of the present application, the identifier information of the target network element may be any one of Fully Qualified Domain Name (FQDN) information and IP address information.

[0232] In an embodiment of the present application, the model platform information supported by the target network element is used to indicate the platforms that the network element can understand and use, such as TensorFlow, PyTorch, etc.

[0233] Optionally, in the embodiment of the present application, the target network element may be based on the model platform training model, or the model may be obtained based on the model platform training.

[0234] In the embodiment of the present application, the model description method information supported by the target network element is used to instruct this network element to describe the method technology used by the model.

[0235] Optionally, in the embodiment of the present application, the model description method information supported by the target network element is one of model format information and model language information.

[0236] Optionally, in the embodiment of the present application, the model language information may be ONNX (One Universal Model Description Language) language.

[0237] Optionally, in the embodiment of the present application, the target network element supports expressing the trained model in model format information or model language information.

[0238] Optionally, in an embodiment of the present application, the model accuracy information achievable by the target network element is used to instruct the target network element to describe the degree of accuracy of identification or decision-making that can be achieved after training the model.

[0239] In an embodiment of the present application, the model accuracy information may be the number of times the model decision result is correct divided by the total number of decisions, that is, model accuracy=number of correct results / total number.

[0240] Optionally, in the embodiment of the present application, the model accuracy information may be identified in the form of a decimal, a percentage, or high, medium, or low.

[0241] Optionally, in the embodiments of the present application, the model training speed information of the target network element may be the time required for the target network element to obtain a model of a certain accuracy through training. For example, if the target network element trains one type of model and requires 2 hours to achieve 90% accuracy, this time represents the model training speed information of the target network element.

[0242] Optionally, in the embodiments of the present application, the algorithm information used for the target network element training model may be an algorithm type related to AI such as machine learning that the target network element supports when training the model, such as deep learning, linear regression, gradient descent, etc., and this algorithm information can be used to obtain the model supported by the target network element.

[0243] Optionally, in the embodiment of the present application, the manufacturer information of the target network element is used to indicate the manufacturer information to which this network element belongs.

[0244] In the embodiment of the present application, the network element target information with which the target network element can share a model is used to indicate the network element target information limited by this network element itself during model sharing and model transmission.

[0245] Optionally, in an embodiment of the present application, the target information of network elements with which the target network element can share a model includes at least one of information of one or more model inference function network elements and information of one or more model training function network elements.

[0246] Optionally, in an embodiment of the present application, the restriction condition information under which the target network element shares the model includes at least one of time restriction condition information and area restriction condition information.

[0247] In an embodiment of the present application, the above-mentioned time restriction condition information is used to indicate the time during which the target network element allows model sharing, for example, from 7 p.m. to 6 a.m. the next day, and the area restriction condition information is used to indicate the area during which the target network element allows model sharing, for example, the location of the network element that will share the model with the target network element should be within this area restriction information, for example, "Suzhou."

[0248] In the examples of the present application, network element information storing a model trained by the first network element; teeth, used to indicate a network element that stores a model trained by the first network element. .

[0249] Optionally, in the embodiments of the present application, network element information storing a model trained by the first network element; may be the identifier information of the network element responsible for storing the model information, such as the ADRF network element, network element type information, etc.

[0250] An embodiment of the present application provides a model request method, in which a third network element can search for a target network element in a second network element through a search request, and the search request includes model training related capability information required by the third network element, so that the second network element can quickly and accurately search for the target network element required by the third network element, and can request the target network element to obtain a model through a model request, and because the model request includes second information, the third network element can obtain model information matching the second information from the first network element, thereby improving the success rate of model transmission.

[0251] It should be mentioned that in the model request method according to the embodiment of the present application, the execution body may be a model request device or a control module for executing the model request method in the model request device.

[0252] The following describes in detail the interaction process of the network element registration method and the model request method according to the embodiment of the present application through a specific embodiment.

[0253] As shown in FIG. 11, the method according to the embodiment of the present application includes the following steps 21 to 28.

[0254] Step 21: The model training network element MTLF (or NWDAF, NWDAF containing MTLF) sends a network element registration message to the NRF to register its capabilities.

[0255] In an embodiment of the present application, a MTLF network element may be registered via (Nnrf_NFManagement_NFRegister Register).

[0256] Step 22: The NRF network element stores the information of this MTLF network element.

[0257] Step 23: The NRF network element sends a registration response message.

[0258] In an embodiment of the present application, the NRF network element may notify the MTLF network element of successful registration via a (Nnrf_NFManagement_NFRegister response) response message.

[0259] The steps are similar to those of the conventional method, but the differences are as follows:

[0260] In step 21, when the MTLF sends a capability registration message to the NRF, it sends information such as its own identifier, supported analytic IDs, as well as "supported training type information," "supported federated learning time," and "metadata information."

[0261] The information required for registration is as follows:

[0262] 1. NF type: Network element type, which refers to the type of network element registered this time. In this scheme, NF type = NWDAF type, etc.

[0263] 2. NF instance ID, FQDN or IP address of NF, refers to the network element instance identifier information registered this time, such as its FQDN information (fully qualified) Domain Name, a fully qualified domain name to indicate the location of this network element and its connectivity) or IP address information (another identifier information).

[0264] 3. Supported analytic ID information, indicating the task types that this NWDAF network element can perform.

[0265] In addition, the network element registration information must further include at least one of model training capability information and training capability information.

[0266] 4. Supported model platform information, which indicates the platforms that this network element understands and can use, such as TensorFlow, PyTorch, etc.

[0267] 5. Supported model description method information refers to the method technology used by the description model, and may be model format information or model language information. For example, the language used in the description model is ONNX (One General-Purpose Model Description Language).

[0268] 6. Model accuracy information. Accuracy is used to describe the accuracy of discrimination or decision-making that can be achieved after training a model. Model accuracy can be calculated by dividing the number of correct model decision results by the total number of decisions, where accuracy = number of correct results / total number. This information can be expressed in the form of a decimal, a percentage, or high, medium, or low.

[0269] 7. Model training speed information, which may be the time required for a first network element to obtain a model with a certain accuracy through training. For example, if this network element trains a model and it takes 2 hours to achieve 90% accuracy, this represents the model training speed of this network element.

[0270] Other Information: 8. Algorithm information used in training the model, including the type of AI-related algorithms such as machine learning that are supported when training the model, such as "deep learning," "linear regression," and "gradient descent."

[0271] 9. Manufacturer information, which is the manufacturer information to which this network element belongs.

[0272] 10. Version information: the version information of the model used by this network element.

[0273] 11. Network element target information that can be used for model sharing, which refers to the network element target information limited by this network element itself when model sharing or model transmission.

[0274] 12. Network element information of the stored training model, including the network element responsible for storing the model information, such as the identifier information of the ADRF (Analytics Data Repository Function), network element type information, etc.

[0275] 13. Information on the limitations on model sharing, including:

[0276] Supported time information indicates the times during which this network element can propagate the model, for example, from 7pm to 6am the next day.

[0277] Area limitation information refers to the range information of the location of the sharing network elements that this network element can accept. For example, the locations of the network elements that share models with this network element should all be within this area limitation information, for example, "Suzhou."

[0278] 14. First indication information, which is used to indicate whether the model training network element supports module sharing or model interoperation with other network elements.

[0279] Step 24: The task consumer sends a task request to AnLF.

[0280] Step 25, the AnLF sends a request to the NRF to find suitable training network elements.

[0281] Step 26: The NRF sends a response message regarding the network element search.

[0282] In the embodiment of the present application, the response message must include: 1. query validity period; 2. identifier information of each network element; 3. address information, etc.

[0283] 4. Model platform information of the searched network elements; 5. Model description method information; 6. Model accuracy information and 7. Model training speed information and 8. Information about the algorithm used to train the model; 9. Manufacturer and version information, 10. Network element information of memory training model; 11. It may further include limited information for sharing the model.

[0284] Step 27, the AnLF initiates a model request to the appropriate network element based on the information returned from the NRF.

[0285] In step 28, AnLF uses the resulting model to generate analytical data and return it to the consumer.

[0286] In an embodiment of the present application, the AnLF may generate a task report after using the model requested in step 27 and return it to the consumer NF, and the AnLF may return the task report to the consumer via (Nnwdaf_AnalyticsInfo_Request response).

[0287] The steps are similar to those of the conventional method, but the differences are as follows:

[0288] In step 25, when the AnLF sends a request to the NRF to find suitable training network elements, the request includes information such as the analytic ID, and may also include "model platform information" and "required time information." This information includes:

[0289] 1. Required Information: Analytic ID, which indicates the task types that the target MTLF can support.

[0290] 2. Filter info: This is task model limitation information, and is used to limit task details, such as the target of the model (e.g., mobility analysis for a certain UE), target task time, etc.

[0291] In this way, the AnLF may limit information about the model propagation, Training capability information, including:

[0292] 3. Supported model platform information, which indicates the platforms that this network element understands and can use, such as TensorFlow, PyTorch, etc.

[0293] 4. Supported model description method information, which refers to the method technology used by the description model, can be model format information or model language information.

[0294] 5. Model accuracy information. Accuracy is used to describe the accuracy of discrimination or decision-making that can be achieved after training a model. Model accuracy may be calculated by dividing the number of correct model decision results by the total number of decisions, where accuracy = number of correct results / total number. This information may be expressed in the form of a decimal, a percentage, or high, medium, or low.

[0295] 6. Model training speed information, which may be the time required for a first network element to obtain a model with a certain accuracy through training. For example, if this network element trains a model and it takes 2 hours to achieve 90% accuracy, this represents the model training speed of this network element.

[0296] Other information, including:

[0297] 7. Algorithm information used in training the model, including the type of AI-related algorithms such as machine learning that are supported when training the model, such as "deep learning," "linear regression," and "gradient descent."

[0298] 8. Manufacturer information, which is the manufacturer information to which this network element belongs.

[0299] 9. Version information: the version information of the model used by this network element.

[0300] 10. Network element target information that can be used for model sharing, which refers to the network element target information limited by this network element itself when model sharing or model transmission is performed.

[0301] 11. Network element information of the stored training model, including the network element responsible for storing the model information, such as the identifier information of the ADRF (Analytics Data Repository Function), network element type information, etc.

[0302] 12. Information on the limitations on model sharing, including:

[0303] Supported time information indicates the times during which this network element can propagate the model, for example, from 7pm to 6am the next day.

[0304] Area limitation information refers to the range information of the location of the sharing network elements that this network element can accept. For example, the locations of the network elements that share models with this network element should all be within this area limitation information, for example, "Suzhou."

[0305] Step 27 (which may be specifically) the AnLF sends a model request to the MTLF.

[0306] In an embodiment of the present application, AnLF may send a model request via (Nnwdaf_MLMoldelInfo_Request), which should include analytic ID, ML model Filter Information, etc.

[0307] It should be noted that for the relevant explanations and beneficial effects of the above steps 21 to 27, please refer to the descriptions in the above embodiments, and no further explanations will be given here.

[0308] 12 shows a possible structural schematic diagram of a network element registration device according to an embodiment of the present application. As shown in FIG. 12, a network element registration device 80 may include: a sending module 81.

[0309] Wherein, the sending module 81 is used to send a network element registration request to the second network element, and the network element registration request is used to register information of the first network element to the second network element, and the information of the first network element includes model training related capability information of the first network element, where the model training related capability information of the first network element includes model platform information supported by the first network element, model description method information supported by the first network element, manufacturer information of the first network element, and Network element target information of a model in which the first network element can be shared and at least one of first indication information for indicating whether the first network element supports model sharing or model interoperation with other network elements, model accuracy information achievable by the first network element, and model training speed information of the first network element.

[0310] An embodiment of the present application provides a network element registration device, which can register the network element information of a first network element with a second network element through a network element registration request, thereby realizing the registration of the first network element with the second network element. Since the network element registration information of the first network element includes model training related capability information, other network elements can search for a first network element that meets the model training needs through the second network element, thereby solving the problem of how the first network element registers its network element information with the second network element and can be searched by other network elements.

[0311] In one possible implementation manner, the model description method information supported by the first network element is either model format information or model language information, where the first network element supports expressing the trained model in model format information or model language information.

[0312] In one possible implementation, the information of the first network element is: Algorithm information used when the first network element trains the model and manufacturer information of the first network element; Network element target information of a model in which the first network element can be shared and limiting condition information for the first network element to share the model; network element information storing a model trained by the first network element; and

[0313] In one possible implementation, Network element target information of a model in which the first network element can be shared includes at least one of information of one or more model inference function network elements and information of one or more model training function network elements.

[0314] In one possible implementation, the restriction condition information under which the first network element shares the model includes at least one of time restriction condition information and area restriction condition information, where the time restriction condition information is used to indicate the time during which the first network element allows the model to be shared, and the area restriction condition information is used to indicate the area during which the first network element allows the model to be shared.

[0315] In one possible implementation, network element information storing a model trained by the first network element; teeth, used to indicate a network element that stores a model trained by the first network element. .

[0316] The network element registration device according to the embodiment of the present application can realize each process realized by the first network element in the above method embodiment and achieve the same technical effect, and will not be further described here to avoid repetition of description.

[0317] 13 shows a possible structural schematic diagram of a network element registration device according to an embodiment of the present application. As shown in FIG. 13, a network element registration device 90 may include: a receiving module 91.

[0318] Here, the receiving module 91 is used to receive a network element registration request sent by a first network element, and the network element registration request is used to register information of the first network element to a second network element, and the information of the first network element includes model training related capability information of the first network element, where the model training related capability information of the first network element includes model platform information supported by the first network element, model description method information supported by the first network element, manufacturer information of the first network element, and Network element target information of a model in which the first network element can be sharedand at least one of first indication information for indicating whether the first network element supports model sharing or model interoperation with other network elements, model accuracy information achievable by the first network element, and model training speed information of the first network element.

[0319] An embodiment of the present application provides a network element registration device, which can receive a network element registration request sent by a first network element, thereby registering the network element information of the first network element with a second network element, thereby realizing the registration of the first network element with the second network element. Since the network element registration information of the first network element includes model training related capability information, other network elements can search for first network elements that meet the model training needs through the second network element, thereby solving the problem of how the first network element registers its network element information with a second network element and can be searched by other network elements.

[0320] In one possible implementation, the receiving module 91 is further used to receive a search request sent by a third network element, the search request being used to request a search for a target network element, and the search request includes at least one of model training related capability information required by the third network element and first information, where the model training related capability information required by the third network element includes at least one of model platform information supported by the target network element required by the third network element, model description method information supported by the target network element required by the third network element, model accuracy information achieved by the target network element required by the third network element, and model training speed information of the target network element required by the third network element. The first information includes at least one of algorithm information used in the training model of the target network element required by the third network element, manufacturer information of the target network element required by the third network element, limiting condition information for model sharing by the target network element required by the third network element, identifier information of the third network element, and model sharing instruction information; Here, the restriction condition information for the target network element required by the third network element to share the model includes at least one of time information supported by the target network element and area restriction information of the target network element.

[0321] In one possible implementation manner, the network element registration device 90 according to the embodiment of the present application further includes a determination module, which is used after the receiving module 91 receives the search request sent by the third network element to determine a target network element based on the search request, and the model training related capability information of the target network element matches the model training related capability information required by the third network element.

[0322] In one possible implementation manner, the determination module specifically determines the target network element based on model platform information supported by the target network element required by the third network element, where the target network element supports the model platform information required by the third network element; or determines the target network element based on model description method information supported by the target network element required by the third network element, where the target network element supports the model description method information required by the third network element; or determines the target network element based on model accuracy information achieved by the target network element required by the third network element, where the target network element supports the model accuracy information to be achieved required by the third network element; or determines the target network element based on model training speed information of the target network element required by the third network element, where the target network element is used to support the model training speed information required by the third network element.

[0323] In one possible implementation manner, the determination module specifically determines the target network element based on algorithm information used in the training model of the target network element required by the third network element, where the target network element supports the algorithm information used in the training model required by the third network element; or determines the target network element based on manufacturer information of the target network element required by the third network element, where the target network element supports the manufacturer information required by the third network element; or determines the target network element based on restriction condition information for model sharing required by the third network element, where the target network element supports the restriction condition information for model sharing required by the third network element; or determines the target network element based on identifier information of the third network element, where the target network element object information with which the target network element can share the model matches the identifier information of the third network element; or determines the target network element based on instruction information shared by the model, where the target network element is used to support model sharing or model interoperation with other network elements.

[0324] In one possible implementation manner, the network element registration device 90 according to the embodiment of the present application further includes a sending module, which is used to send a search response to the third network element after the determination module determines the target network element based on the search request, where the search response includes target information, which includes at least one of: identifier information of the target network element, address information of the target network element, model platform information supported by the target network element, model description method information supported by the target network element, model accuracy information achievable by the target network element, model training speed information of the target network element, algorithm information used in the training model of the target network element, manufacturer information of the target network element, restriction condition information for the target network element to share the model, and network element information of the training model stored in the target network element.

[0325] The network element registration device according to the embodiment of the present application can realize each process realized by the second network element in the above method embodiment and achieve the same technical effect, and will not be further described here to avoid repetition of description.

[0326] 14 shows a possible structural schematic diagram of a model requesting device according to an embodiment of the present application. As shown in FIG. 14, the model requesting device 100 may include: a sending module 101 and an acquiring module 102.

[0327] Here, the sending module 101 is used to send a model request message to a first network element, and the model request message is used to request the acquisition of a model, where the model request message includes second information, and the second information includes at least one of model platform information, model description method information, model accuracy information, manufacturer information of a third network element, and identifier information of the third network element, and the acquiring module 102 is used by the third network element to acquire information of a model matching the second information from the first network element.

[0328] An embodiment of the present application provides a model request device, which can request a first network element to obtain a model through a model request, and since the model request includes second information, a third network element can obtain model information matching the second information from the first network element, thereby improving the success rate of model transmission.

[0329] In one possible implementation, the model description method information is one of model format information and model language information, and the model description method information is used to instruct the first network element to feed back the model to the third network element in the model format information or the model language information.

[0330] In one possible implementation, the second information further includes at least one of algorithm information used in the training model, model version information, and model feedback time information.

[0331] In one possible implementation, the model information includes at least one of: file information of the model; and download address information of the model file.

[0332] In one possible implementation manner, the sending module 101 is further used to send a search request to the second network element, the search request is used to request a search for a target network element, and the search request includes at least one of model training related capability information required by the third network element and first information, where the model training related capability information required by the third network element includes: model platform information supported by the target network element required by the third network element; model description method information supported by the target network element required by the third network element; manufacturer information of the first network element; Network element target information of a model in which the first network element can be shared and first indication information for indicating whether the first network element supports model sharing or model interoperation with other network elements, model accuracy information achieved by the target network element required by the third network element, and model training speed information of the target network element required by the third network element, where the first information includes at least one of algorithm information used in the training model of the target network element required by the third network element, manufacturer information of the target network element required by the third network element, restriction condition information under which the target network element required by the third network element performs model sharing, identifier information of the third network element, and model sharing indication information, where the restriction condition information under which the target network element required by the third network element performs model sharing includes at least one of time information supported by the target network element and area restriction information of the target network element.

[0333] The model sharing indication information is used to indicate that the network element required by the third network element is a network element that supports model sharing or model interoperation with other network elements.

[0334] In one possible implementation manner, the model request device 100 according to the embodiment of the present application further includes a receiving module, which is used to receive a search response sent by the second network element after the sending module 101 sends a search request to the second network element, where the search response includes target information, which includes at least one of: identifier information of the target network element, address information of the target network element, model platform information supported by the target network element, model description method information supported by the target network element, model accuracy information achievable by the target network element, model training speed information of the target network element, algorithm information used in the training model of the target network element, manufacturer information of the target network element, restriction condition information for model sharing by the target network element, and network element information of the training model stored in the target network element.

[0335] The model request device according to the embodiment of the present application can implement each process implemented by the third network element in the above method embodiment and achieve the same technical effect, and will not be further described here to avoid repetition of description.

[0336] 15 shows a possible structural schematic diagram of a model requesting device according to an embodiment of the present application. As shown in FIG. 15, the model requesting device 110 may include: a receiving module 111.

[0337] Here, the receiving module 111 is used to receive a model request message sent by a third network element, and the model request message is used to request the acquisition of a model, where the model request message includes second information, and the second information includes at least one of model platform information, model description method information, model accuracy information, manufacturer information of the third network element, and identifier information of the third network element, where the second information is used by the third network element to acquire information of a model matching the second information from the first network element.

[0338] An embodiment of the present application provides a model request device, which can receive a model request sent by a third network element, and since the model request includes second information, the third network element can obtain model information matching the second information from the first network element, thereby improving the success rate of model transmission.

[0339] In one possible implementation, the model description method information is one of model format information and model language information, and the model description method information is used to instruct the first network element to feed back the model to the third network element in the model format information or the model language information.

[0340] In one possible implementation, the second information further includes at least one of algorithm information used in the training model, model version information, and model feedback time information.

[0341] In one possible implementation, the model information includes at least one of: file information of the model; and download address information of the model file.

[0342] The model request device according to the embodiment of the present application can implement each process implemented by the first network element in the above method embodiment and achieve the same technical effect, and will not be further described here to avoid repetition of description.

[0343] Optionally, as shown in FIG. 16, an embodiment of the present application further provides a communication device 5000, which includes a processor 5001 and a memory 5002, and the memory 5002 stores a program or instruction that can run on the processor 5001. For example, if the communication device 5000 is a network element, when the program or instruction is executed by the processor 5001, it can realize each step of the embodiment of the first network element side network element registration method and achieve the same technical effect, or it can realize each step of the embodiment of the second network element side network element registration method and achieve the same technical effect, or it can realize each step of the embodiment of the third network element side model request method and achieve the same technical effect, or it can realize each step of the embodiment of the first network element side model request method and achieve the same technical effect. In order to avoid repetition of description, no further description will be given here.

[0344] An embodiment of the present application further provides a network element, including a processor and a communication interface, wherein the communication interface is used to send a network element registration request to a second network element, and the network element registration request is used to register information of a first network element to the second network element, and the information of the first network element includes model training related capability information of the first network element, where the model training related capability information of the first network element includes model platform information supported by the first network element, model description method information supported by the first network element, manufacturer information of the first network element, and Network element target information of a model in which the first network element can be shared and at least one of first indication information for indicating whether the first network element supports model sharing or model interoperation with other network elements, model accuracy information achievable by the first network element, and model training speed information of the first network element. This network element embodiment corresponds to the first network element-side method embodiment, and the implementation processes and realization manners of the method embodiment are all applicable to this network element embodiment, and can achieve the same technical effects.

[0345] An embodiment of the present application further provides a network element, including a processor and a communication interface, wherein the communication interface is used to receive a network element registration request sent by a first network element, and the network element registration request is used to register information of the first network element to a second network element, and the information of the first network element includes model training related capability information of the first network element, where the model training related capability information of the first network element includes model platform information supported by the first network element, model description method information supported by the first network element, manufacturer information of the first network element, and Network element target information of a model in which the first network element can be shared and at least one of first indication information for indicating whether the first network element supports model sharing or model interoperation with other network elements, model accuracy information achievable by the first network element, and model training speed information of the first network element. This network element embodiment corresponds to the second network element-side method embodiment, and the implementation processes and realization manners of the method embodiments are all applicable to this network element embodiment, and can achieve the same technical effects.

[0346] An embodiment of the present application further provides a network element, including a processor and a communication interface, wherein the communication interface is used to send a model request message to a first network element, the model request message is used to request acquisition of a model, where the model request message includes second information, the second information including at least one of model platform information, model description method information, model accuracy information, manufacturer information of a third network element, and identifier information of the third network element, and the third network element acquires information of a model matching the second information from the first network element. This embodiment of the network element corresponds to the embodiment of the third network element-side method, and the implementation processes and realization manners of the embodiment of the method are all applicable to this embodiment of the network element, and can achieve the same technical effects.

[0347] An embodiment of the present application further provides a network element, including a processor and a communication interface, wherein the communication interface is used to receive a model request message sent by a third network element, the model request message being used to request acquisition of a model, where the model request message includes second information, the second information including at least one of model platform information, model description method information, model accuracy information, manufacturer information of the third network element, and identifier information of the third network element, where the second information is used by the third network element to acquire information of a model matching the second information from the first network element. This embodiment of the network element corresponds to an embodiment of the above-mentioned model request method-side first network element method, and the implementation processes and realization manners of the above-mentioned method embodiments are all applicable to this embodiment of the network element, and can achieve the same technical effects.

[0348] Specifically, Figure 17 is a schematic diagram of a hardware structure for implementing a network element in an embodiment of the present application, where the network element is a first network element, or the network element is a second network element, or the network element is a third network element.

[0349] 17, the network element 1200 includes a processor 1201, a network interface 1202, and a memory 1203. Here, the network interface 1202 is, for example, a common public wireless interface.

[0350] Specifically, the network element 1200 of the embodiment of the present application further includes instructions or programs stored in the memory 1203 and capable of running on the processor 1201, and the processor 1201 can call the instructions or programs in the memory 1203, execute the methods performed by each of the above modules, and achieve the same technical effects, which will not be described further here to avoid repetition.

[0351] The network element according to the embodiment of the present application can realize each process realized by the first network element, the second network element and the third network element in the above method embodiment, and can achieve the same technical effect, and will not be further described here to avoid repetition of description.

[0352] The embodiments of the present application further provide a readable storage medium, which stores a program or instruction, and when the program or instruction is executed by a processor, it can realize each process of the above method embodiments and achieve the same technical effect, and in order to avoid repetition of description, it will not be further described here.

[0353] Here, the processor is the processor in the communication device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0354] The embodiments of the present application further provide a chip, the chip including a processor and a communication interface, the communication interface coupled to the processor, the processor running a program or instruction, used to realize each process of the above method embodiments, and can achieve the same technical effect, and in order to avoid repetition of description, it will not be further described here.

[0355] It should be understood that the chips referred to in the embodiments of this application may be referred to as system level chips, system chips, chip systems, or system-on-chips.

[0356] The embodiments of the present application further provide a computer program / program product, which is stored in a storage medium, and which can be executed by at least one processor to realize each process of the above method embodiments and achieve the same technical effects, and will not be further described here to avoid repetition.

[0357] An embodiment of the present application further provides a communication system, which includes a first network element, a second network element and a third network element, wherein the first network element may be used to perform steps of the network element registration method described above and may be used to perform steps of the model request method described above, the second network element may be used to perform steps of the network element registration method described above, and the third network element may be used to perform steps of the model request method described above.

[0358] It should be noted that, in this specification, the terms "comprise," "include," "includes," or any other variations thereof are intended to cover the non-exclusive "comprise," whereby a process, method, article, or apparatus comprising a set of elements not only includes those elements, but also other elements not expressly listed or inherent in such process, method, article, or apparatus. Absent further limitations, an element defined by the phrase "comprises one of" does not preclude the presence of other identical elements in the process, method, article, or apparatus comprising that element. It should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may include performing functions in an essentially simultaneous manner or in the reverse order based on the functions involved. For example, the described method may be performed in a different order than described, and various steps may be added, omitted, or combined. Furthermore, features described with reference to some examples may be combined in other examples.

[0359] As will be apparent to those skilled in the art from the above description of the embodiments, the methods of the above embodiments can be realized in the form of software and a necessary general-purpose hardware platform. Of course, they can also be realized in hardware, but in many cases the former is a more preferred embodiment. Based on this understanding, the technical proposal of the present application, in substance or in part contributing to the prior art, may be embodied in the form of a computer software product, which is stored in a storage medium (e.g., ROM / RAM, magnetic disk, optical disk) and includes a number of instructions for causing a terminal (which may be a mobile phone, computer, server, air conditioner, network device, etc.) to execute the methods described in each embodiment of the present application.

[0360] Although the embodiments of the present application have been described above in conjunction with the drawings, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not limiting. Those skilled in the art can take the teachings of the present application into account and implement many forms without departing from the spirit and scope of the claims, all of which fall within the scope of protection of the present application.

[0361] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority from Chinese Patent Application No. 202210317248.5 filed in China on March 28, 2022, and from Chinese Patent Application No. 202210370099.9 filed in China on April 8, 2022, the entire contents of which are incorporated herein by reference.

Claims

1. A network element registration method, comprising: a first network element sending a network element registration request to a second network element, the network element registration request being used to register information of the first network element with the second network element, the information of the first network element including model training related capability information of the first network element; Wherein, the model training related capability information of the first network element is: Network element target information of a model that the first network element can share; and first indication information for indicating whether the first network element supports model sharing or model interoperation with other network elements.

2. The model training related capability information of the first network element further includes model description method information supported by the first network element; The model description method information supported by the first network element is one of model format information and model language information; The network element registration method according to claim 1 , wherein the first network element supports expressing a trained model in the model format information or the model language information.

3. The information of the first network element includes: Algorithm information used when the first network element performs model training; Limitation condition information for the first network element to share a model; and network element information storing a model trained by the first network element.

4. The network element registration method according to claim 1, wherein the network element target information of the model that can be shared by the first network element includes at least one of information of one or more model inference function network elements and information of one or more model training function network elements.

5. The limitation condition information under which the first network element shares a model includes at least one of time limitation condition information and area limitation condition information; wherein the time restriction condition information is used to indicate a time during which the first network element allows model sharing, and the area restriction condition information is used to indicate an area during which the first network element allows model sharing; and / or 4. The network element registration method according to claim 3, wherein the network element information storing the model trained by the first network element is used to indicate the network element storing the model trained by the first network element.

6. A network element registration method, comprising: receiving, by a second network element, a network element registration request sent by a first network element, the network element registration request being used to register information of the first network element with the second network element, the information of the first network element including model training related capability information of the first network element; Wherein, the model training related capability information of the first network element is: Network element target information of a model that the first network element can share; and first indication information for indicating whether the first network element supports model sharing or model interoperation with other network elements.

7. After the second network element receives a network element registration request sent by the first network element, the network element registration method includes: The method further includes the second network element receiving a search request sent by a third network element, the search request being used to request a search for a target network element, the search request including at least one of model training related capability information and first information required by the third network element; Wherein, the model training related capability information required by the third network element includes at least one of: model platform information supported by the target network element required by the third network element; model description method information supported by the target network element required by the third network element; model accuracy information achieved by the target network element required by the third network element; and model training speed information of the target network element required by the third network element; The first information includes at least one of algorithm information used in the target network element training model required by the third network element, manufacturer information of the target network element required by the third network element, limiting condition information under which the target network element required by the third network element shares a model, identifier information of the third network element, and instruction information shared by the model; Here, the restriction condition information for the target network element required by the third network element to share a model includes at least one of time information supported by the target network element and area restriction information of the target network element.

8. After the second network element receives a search request sent by the third network element, the network element registration method includes: The second network element further determines the target network element based on the search request, and the model training related capability information of the target network element matches the model training related capability information required by the third network element; determining the target network element based on the search request by the second network element; The second network element determines the target network element based on model platform information supported by the target network element required by the third network element, where the target network element supports the model platform information required by the third network element; The second network element determines the target network element based on model description method information supported by the target network element required by the third network element, and the target network element supports the model description method information required by the third network element; The second network element determines the target network element based on model accuracy information that the third network element requires to be achieved by the target network element, and the target network element supports the model accuracy information that the third network element requires to be achieved; 8. The network element registration method of claim 7, further comprising at least one of: the second network element determining the target network element based on model training speed information of the target network element required by the third network element; and the target network element supporting the model training speed information required by the third network element.

9. After the second network element receives a search request sent by the third network element, the network element registration method includes: The second network element further includes determining a target network element based on first information in the search request; determining the target network element based on first information in the search request by the second network element; The second network element determines the target network element based on algorithm information used in the target network element training model required by the third network element, and the target network element supports the algorithm information used in the training model required by the third network element; The second network element determines the target network element based on manufacturer information of the target network element required by the third network element, and the target network element supports the manufacturer information required by the third network element; The second network element determines the target network element based on the limiting condition information of the target network element that the third network element requests to share a model, and the target network element supports the limiting condition information of the model that the third network element requests to share; The second network element determines the target network element according to the identifier information of the third network element, and the network element target information that the target network element can share a model with matches the identifier information of the third network element; 7. The network element registration method according to claim 6, further comprising: the second network element determining the target network element based on instruction information shared by the model, and the target network element supporting model sharing or model interoperation with other network elements.

10. After the second network element determines the target network element based on the search request, the network element registration method includes:

9. The network element registration method of claim 8, further comprising: the second network element sending a search response to the third network element, wherein the search response includes target information, the target information including at least one of identifier information of the target network element, address information of the target network element, model platform information supported by the target network element, model description method information supported by the target network element, model accuracy information achievable by the target network element, model training speed information of the target network element, algorithm information used in the training model of the target network element, manufacturer information of the target network element, restriction condition information for model sharing by the target network element, and network element information of the training model stored in the target network element.

11. 1. A model request method, comprising: a third network element sending a model request message to a first network element, the model request message being used to request acquisition of a model, wherein the model request message includes second information, the second information including at least one of model platform information, model description method information, model accuracy information, manufacturer information of the third network element, and identifier information of the third network element; A model request method, in which the third network element obtains information of a model that matches the second information from the first network element.

12. Before the third network element sends a model request message to the first network element, the model request method includes: The third network element further includes sending a search request to the second network element, the search request being used to request a search for a target network element, and the search request includes at least one of model training related capability information and first information required by the third network element; Wherein, the model training related capability information required by the third network element includes at least one of: model platform information supported by the target network element required by the third network element; model description method information supported by the target network element required by the third network element; model accuracy information achieved by the target network element required by the third network element; and model training speed information of the target network element required by the third network element; The first information includes at least one of algorithm information used in the target network element training model required by the third network element, manufacturer information of the target network element required by the third network element, and limiting condition information under which the target network element required by the third network element shares a model; Here, the model request method described in claim 11, wherein the restriction condition information for the target network element requested by the third network element to share the model includes at least one of time information supported by the target network element and area restriction information of the target network element.

13. After the third network element sends a search request to the second network element, the model request method includes:

13. The model request method of claim 12, further comprising: the third network element receiving a search response sent by the second network element, the search response including target information, the target information including at least one of identifier information of the target network element, address information of the target network element, model platform information supported by the target network element, model description method information supported by the target network element, model accuracy information achievable by the target network element, model training speed information of the target network element, algorithm information used in the training model of the target network element, manufacturer information of the target network element, information on restriction conditions under which the target network element shares a model, and network element information of the training model stored in the target network element.

14. 1. A model request method, comprising: The method includes: a first network element receiving a model request message sent by a third network element, the model request message being used to request acquisition of a model; and the model request message including second information, the second information including at least one of model platform information, model description method information, model accuracy information, manufacturer information of the third network element, and identifier information of the third network element; Here, the second information is used by the third network element to obtain information of a model that matches the second information from the first network element.

15. The model request method further includes the first network element obtaining, based on the second information, information of a model matching the second information; The first network element obtaining, based on the second information, information of a model matching the second information, The first network element acquires a target model based on model platform information included in the second information, and the target model is generated based on a model platform corresponding to the model platform information; 15. The model request method according to claim 14, comprising at least one of: the first network element acquiring a target model based on model description method information included in the second information, and the target model being represented based on model language information or model format information corresponding to the model description method information.

16. The model request method includes: The first network element determines, based on manufacturer information of the third network element included in the second information, that the first network element allows model sharing or model interoperation with the third network element; and determining, by the first network element, based on identifier information of the third network element included in the second information, that the first network element allows model sharing or model interoperation with the third network element.

17. A network element comprising a processor and a memory, the memory storing a program or instruction operable on the processor, the program or instruction implementing the steps of the network element registration method according to any one of claims 1 to 5 when executed by the processor.

18. A network element comprising a processor and a memory, the memory storing a program or instruction operable on the processor, the program or instruction implementing the steps of the network element registration method according to any one of claims 6 to 10 when executed by the processor.

19. A network element comprising a processor and a memory, the memory storing a program or instructions operable on the processor, the program or instructions, when executed by the processor, realizing the steps of the model request method of any one of claims 11 to 13.

20. 17. A network element comprising a processor and a memory, the memory storing a program or instructions operable on the processor, the program or instructions, when executed by the processor, realizing the steps of the model request method of any one of claims 14 to 16.

21. A readable storage medium having a program or instructions stored therein, the program or instructions being, when executed by a processor, to implement steps of a network element registration method according to any one of claims 1 to 5, or to implement steps of a network element registration method according to any one of claims 6 to 10, or to implement steps of a model request method according to any one of claims 11 to 13, or to implement steps of a model request method according to any one of claims 14 to 16.

Images