A network data analysis method, functional entity and electronic device

Abstract

The present invention provides a network data analysis method, a functional entity and an electronic device, the network data analysis method comprising: requesting a first object to generate a model information, the first object being a training platform, a training module, a training functional entity or a training service module, and receiving the model information sent by the first object. Since the first object and the NWDAF are two separate entities, the first object with a model training function can be used by multiple NWDAFs, thereby improving flexibility.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a network data analysis method, a functional entity and an electronic device. Background Art

[0002] The Network Data Analytics Function (NWDAF) entity is set as a complex, including units such as the data lake, training platform, and reasoning platform. The NWDAF entity interacts with each network element to complete data collection, model training, and reasoning operations, and sends training and analysis results to relevant network elements as needed.

[0003] Currently, the overall design of the NWDAF entity includes the model training function, which makes the use of the model training function inflexible. Summary of the invention

[0004] The embodiments of the present invention provide a network data analysis method, a functional entity and an electronic device to solve the problem that the model training function of the NWDAF entity is not flexible enough.

[0005] To solve the above technical problems, the present invention is achieved as follows:

[0006] In a first aspect, an embodiment of the present invention provides a network data analysis method for a network data analysis function entity, the network data analysis method comprising:

[0007] Requesting a first object to generate a model; the first object is a training platform, a training module, a training function entity or a training service module;

[0008] The model sent by the first object is received.

[0009] In a second aspect, an embodiment of the present invention provides a network data analysis method for a network storage repository functional entity, the network data analysis method comprising:

[0010] Receiving a second request message sent by a network data analysis function NWDAF entity;

[0011] A second response message is sent to the NWDAF entity, where the second response message is used to indicate an available second object; the second object is a training platform, a training module, a training function entity or a training service module.

[0012] In a third aspect, an embodiment of the present invention provides a network data analysis method for a training object, wherein the training object includes a training platform, a training module, a training function entity or a training service module, and the network data analysis method includes:

[0013] Receive requests sent by the network data analysis function NWDAF entity and generate models;

[0014] The model is sent to the NWDAF entity.

[0015] In a fourth aspect, an embodiment of the present invention provides a functional entity, wherein the functional entity is a network data analysis functional entity, and the functional entity includes a processor and a transceiver;

[0016] The transceiver is used to request a first object to generate a model and receive the model sent by the first object, where the first object is a training platform, a training module, a training function entity or a training service module.

[0017] In a fifth aspect, an embodiment of the present invention provides a functional entity, wherein the functional entity is a network storage repository functional entity, and the functional entity includes a processor and a transceiver;

[0018] The transceiver is used to receive a second request message sent by a network data analysis function NWDAF entity; send a second response message to the NWDAF entity, and the second response message is used to indicate an available second object; the second object is a training platform, a training module, a training function entity or a training service module.

[0019] In a sixth aspect, an embodiment of the present invention provides a functional entity, the functional entity is a training object, the training object includes a training platform, a training module, a training functional entity or a training service module, and the functional entity includes a processor and a transceiver:

[0020] The transceiver is used to receive a request sent by a network data analysis function NWDAF entity, generate a model, and send the model to the NWDAF entity.

[0021] In a seventh aspect, an embodiment of the present invention provides a functional entity, wherein the functional entity is a network data analysis functional entity, and the functional entity includes:

[0022] A request module, used for requesting a first object to generate a model; the first object is a training platform, a training module, a training function entity or a training service module;

[0023] A receiving module is used to receive the model sent by the first object.

[0024] In an eighth aspect, an embodiment of the present invention provides a functional entity, wherein the functional entity is a network storage repository functional entity, and the functional entity includes:

[0025] A receiving module, configured to receive a second request message sent by a network data analysis function NWDAF entity;

[0026] A sending module is used to send a second response message to the NWDAF entity, where the second response message is used to indicate an available second object; the second object is a training platform, a training module, a training function entity or a training service module.

[0027] In a ninth aspect, an embodiment of the present invention provides a functional entity, wherein the functional entity is a training object, and the training object includes a training platform, a training module, a training functional entity or a training service module, and is characterized in that the functional entity includes:

[0028] A receiving module, used to receive a request sent by a network data analysis function NWDAF entity and generate a model;

[0029] A sending module is used to send the model to the NWDAF entity.

[0030] In a tenth aspect, an embodiment of the present invention provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps in the network data analysis method as described in the first aspect, or, when executed by the processor, implements the steps in the network data analysis method as described in the second aspect, or, when executed by the processor, implements the steps in the network data analysis method as described in the third aspect.

[0031] In the eleventh aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by the processor, the steps of the network data analysis method as described in the first aspect are implemented, or, when the computer program is executed by the processor, the steps of the network data analysis method as described in the second aspect are implemented, or, when the computer program is executed by the processor, the steps of the network data analysis method as described in the third aspect are implemented.

[0032] In the embodiment of the present invention, the network data analysis function entity requests the first object to generate a model, the first object is a training platform, a training module, a training function entity or a training service module, and receives the model sent by the first object. Since the first object and the NWDAF are two separate entities, the first object with the model training function can be used by multiple NWDAFs, which improves flexibility. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0034] Figure 1 This is one of the flow charts of a network data analysis method provided by an embodiment of the present invention;

[0035] Figure 2 This is the second flowchart of a network data analysis method provided by an embodiment of the present invention;

[0036] Figure 3 This is a flowchart of a network data analysis method provided by an embodiment of the present invention;

[0037] Figure 4 is a schematic diagram of information transmission between multiple functional entities provided by an embodiment of the present invention;

[0038] Figure 5 is a structural diagram of a first functional entity provided by an embodiment of the present invention;

[0039] Figure 6 is a structural diagram of a second functional entity provided by an embodiment of the present invention;

[0040] Figure 7 is a structural diagram of a third functional entity provided by an embodiment of the present invention;

[0041] Figure 8 It is a structural diagram of another functional entity provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] In the first version of the 5G standard, 3GPP uses the machine learning-based NWDAF entity as the basis for the network slice selection function and policy control function. In other words, the execution of the network slice selection function and policy control function needs to rely on the NWDAF entity. The NWDAF entity can perform "collection" operations and data processing operations on many types of data, such as real-time monitoring of the traffic load of all 5G network slices, collecting and analyzing user usage behavior of 5G mobile terminals, collecting and analyzing the operating performance of 5G applications, etc., and then use machine learning technology to analyze it in real time and make decisions.

[0044] The specific embodiments of the present invention can be applied to the above-mentioned 5G mobile communication system, but it should be understood that the embodiments of the present invention can also be applied to other networks in which NWDAF or similar functional entities are set.

[0045] The specific embodiments of the present invention are further described in detail below.

[0046] See also Figure 1 , Figure 1 is a flowchart of a network data analysis method provided by an embodiment of the present invention, which is applied to a network data analysis functional entity, such as Figure 1 As shown, the network data analysis method includes the following steps:

[0047] Step 101: Request a first object to generate a model; the first object is a training platform, a training module, a training function entity or a training service module.

[0048] Models can be either statistical or predictive.

[0049] Step 102: Receive the model sent by the first object.

[0050] In this embodiment, the model is generated by the first object and sent to the network data analysis function (Network Data Analytics Function, referred to as NWDAF) entity. The first object and NWDAF are two separate entities. In this way, the first object with the model training function exists separately as a physical entity or logical entity, so that each first object can be used by multiple NWDAFs, thereby improving flexibility.

[0051] In this embodiment, the NWDAF entity requests the first object to generate a model, the first object is a training platform, a training module, a training function entity or a training service module, and receives the model sent by the first object. Since the first object and the NWDAF are two separate entities, the first object with a model training function can be used by multiple NWDAFs, which improves flexibility.

[0052] In one embodiment of the present application, the requesting the first object to generate a model specifically includes:

[0053] Sending a first request message to the first object, where the first request message is used to request the first object to generate the model; the model is carried in a first response message;

[0054] or

[0055] Calling a training service provided by a third object for generating the model; the third object is a training module, a training function entity or a training service module.

[0056] In this embodiment, requesting the first object to generate a model includes two ways: the first way is to request the first object to generate a model by sending a first request message to the first object. The second way is to request the first object to generate a model by calling a training service provided by a third object for generating the model.

[0057] The training module logically belongs to the NWDAF entity, but can be set in the NWDAF entity or deployed in other entities or network elements in terms of physical deployment. The training function entity, training service module and training module are all software logic modules, which are different terms for software implementation.

[0058] In one embodiment of the present application, the first request message includes at least one of the following parameters:

[0059] Algorithm identification parameters, algorithm performance requirement parameters and data address parameters.

[0060] Specifically, the algorithm identification parameter can be used to indicate which algorithm is requested to be used for training, the algorithm performance requirement parameter can be used to indicate the performance requirements of the algorithm requested to be used, and the data address parameter can be used to indicate where to collect data for training.

[0061] In one embodiment of the present application, the first response message includes at least one of the following parameters: a model identifier, a model input parameter, a model output parameter, and a model parameter.

[0062] In one embodiment of the present application, before requesting the first object to generate a model, the method further includes:

[0063] Sending a second request message to the network repository function NRF entity;

[0064] Receive a second response message returned by the NRF entity, where the second response message is used to indicate an available second object; the second object is a training platform, a training module, a training function entity or a training service module; and the first object is selected from the second object.

[0065] Specifically, in the current system architecture, all services, training platforms, etc. are uniformly registered to the network repository function (NF Repository Function, referred to as NRF). Before determining the first object, that is, before the NWDAF entity requests the first object to generate a model, the NRF entity can be informed of the currently available objects to avoid blindly selecting the first object. That is, the NWDAF entity sends a second request message to the NRF entity, requesting the NRF entity to return an available second object.

[0066] Furthermore, the NRDAF entity may propose its own requirements, for example, carry parameters in the second request message, and the parameters are used by the NRF entity to determine the second object, so that the second object determined in this way better meets the requirements of the NRDAF entity. The NRF entity may determine the second object based on the parameters carried in the second request message, and send a second response message to the NWDAF entity, and the second response message is used to indicate the available second object.

[0067] The NWDAF entity receives the second response message returned by the NRF entity, and selects the first object from the second object according to the instruction of the second response message. The second response message carries the parameters of the second object, and the parameters of the second object are used by the NWDAF entity to select the first object from the second object.

[0068] The NRF entity may return multiple second objects. Since the second response message carries the parameters of the second object, this is beneficial for the NWDAF entity to select a suitable first object from multiple second objects, such as selecting an object with high training accuracy or an object with fast training speed.

[0069] In one embodiment of the present application, after receiving the model sent by the first object, the method further includes:

[0070] A model registration message is sent to the NRF entity, where the model registration message includes identification information of the model and address information of a network data analysis function NWDAF entity.

[0071] Specifically, the NWDAF entity sends a model registration message to the NRF entity to complete the registration of the NWDAF entity with the NRF entity, so that the subsequent network function (NF) entity can call and obtain the model.

[0072] Further, if the NWDAF entity requests the first object to generate a model, it is performed based on the request of the NF entity. After receiving the model sent by the first object, the NWDAF entity sends the model to the NF.

[0073] See also Figure 2 , Figure 2is a flowchart of a network data analysis method provided by an embodiment of the present invention, which is applied to a network storage library functional entity, such as Figure 2 As shown, the network data analysis method includes the following steps:

[0074] Step 201: Receive a second request message sent by a network data analysis function NWDAF entity.

[0075] Step 202: Send a second response message to the NWDAF entity, where the second response message is used to indicate an available second object; the second object is a training platform, a training module, a training function entity or a training service module.

[0076] Specifically, before requesting the first object to generate a model, the NWDAF entity may ask the NRF entity to inform the currently available object to avoid blindly selecting the first object. That is, the NWDAF entity sends a second request message to the NRF entity, requesting the NRF entity to return an available second object.

[0077] After receiving the second request message sent by the NWDAF entity, the NRF entity sends a second response message to the NWDAF entity, where the second response message is used to indicate the available second object, so that after obtaining the second object, the NWDAF entity can select the first object from the second object and request the first object to generate a model.

[0078] In this embodiment, a second request message sent by a network data analysis function NWDAF entity is received; a second response message is sent to the NWDAF entity, and the second response message is used to indicate an available second object; the second object is a training platform, a training module, a training function entity, or a training service module. In this way, after obtaining the second object, the NWDAF entity can select the first object from the second object and request the first object to generate a model. Since the first object and the NWDAF are two separate entities, the first object with a model training function can be used by multiple NWDAFs, which improves flexibility.

[0079] In one embodiment of the present application, before receiving the second request message sent by the NWDAF, the method further includes:

[0080] A registration request message is received from an object to be registered; and the second object is selected from objects registered in the network repository function entity NRF.

[0081] In this embodiment, all services, training platforms, etc. can be uniformly registered to the NRF entity. The NRF entity receives a registration request message sent by the object to be registered. After receiving a second request message sent by the NWDAF entity, the NRF entity returns a second response message indicating an available second object to the NWDAF entity. The second object is selected from the objects registered in the NRF.

[0082] Furthermore, the registration request message includes at least one of the following parameters of the object to be registered:

[0083] Address parameters, location parameters, load parameters, algorithm capability parameters, and supported algorithm type parameters.

[0084] Furthermore, the second request message carries parameters, and the parameters are used by the NRF to determine the second object.

[0085] Specifically, the NRDAF entity may propose its own requirements, for example, carry parameters in the second request message, and the parameters are used by the NRF entity to determine the second object, so that the second object determined in this way better meets the requirements of the NRDAF entity. The NRF entity may determine the second object based on the parameters carried in the second request message, and send a second response message to the NWDAF entity, and the second response message is used to indicate the available second object.

[0086] Furthermore, the second response message carries parameters of the second object, and the parameters of the second object are used by the NWDAF to select the first object from the second object.

[0087] Specifically, the NRF entity may return multiple second objects. Since the second response message carries the parameters of the second object, this is conducive to the NWDAF entity selecting a suitable first object from multiple second objects, such as selecting an object with high training accuracy or an object with fast training speed.

[0088] In one embodiment of the present application, after sending the second response message to the NWDAF entity, the method further includes:

[0089] A model registration message sent by the NWDAF entity is received, where the model registration message includes identification information of the model and address information of the NWDAF entity.

[0090] Specifically, the NWDAF entity sends a model registration message to the NRF entity to complete the registration of the NWDAF entity with the NRF entity, so that the subsequent NF entity can call and obtain the model.

[0091] See also Figure 3 , Figure 3is a flowchart of a network data analysis method provided by an embodiment of the present invention, which is applied to a training object, wherein the training object includes a training platform, a training module, a training function entity or a training service module, such as Figure 3 As shown, the network data analysis method includes the following steps:

[0092] Step 301: Receive a request sent by a network data analysis function NWDAF entity and generate a model.

[0093] The training object may be the first object or the third object. The model may be a statistical model or a prediction model.

[0094] Step 302: Send the model to the NWDAF entity.

[0095] The training object sends the generated model to the NWDAF entity.

[0096] In this embodiment, the training object receives a request sent by the network data analysis function NWDAF entity, generates a model, and sends the model to the NWDAF entity. Since the training object has a model training function, and the training object and the NWDAF are two separate entities, the training object with a model training function can be used by multiple NWDAFs, which improves flexibility.

[0097] In one embodiment of the present application, the receiving request sent by the NWDAF entity generates a model specifically as follows:

[0098] After receiving the first request message sent by the NWDAF entity, data training is performed to generate the model;

[0099] or

[0100] Receive a call request for a data training service sent by the NWDAF entity, and provide a training service for generating the model.

[0101] Specifically, the training object can provide two ways to generate models according to the request sent by the NWDAF entity:

[0102] The first way is to perform data training after receiving the first request message sent by the NWDAF entity to generate the model; the second way is to receive a call request for a data training service sent by the NWDAF entity, and provide a training service for generating a model, so that the NWDAF entity can call the training service for generating a model. In this embodiment, the training module logically belongs to the NWDAF entity, but in terms of physical deployment, it can be set in the NWDAF entity, or it can be deployed in other entities or network elements. The training function entity, training service module, and training module are all software logic modules, which are different ways of saying software implementation.

[0103] In one embodiment of the present application, the receiving a request sent by the NWDAF entity, before generating the model, further includes:

[0104] Send a registration request message to the network repository function NRF entity, requesting to register with the NRF entity.

[0105] In this embodiment, the training object can register it with the NRF entity. The NRF entity receives the registration request message sent by the training object, requesting to register with the NRF entity. In this way, after receiving the second request message sent by the NWDAF entity, the NRF entity returns a second response message indicating an available second object to the NWDAF entity. The second object is selected from the objects registered in the NRF.

[0106] In one embodiment of the present application, the first request message includes at least one of the following parameters: an algorithm identification parameter, an algorithm performance requirement parameter, and a data address parameter.

[0107] Specifically, the algorithm identification parameter can be used to indicate which algorithm is requested to be used for training, the algorithm performance requirement parameter can be used to indicate the performance requirements of the algorithm requested to be used, and the data address parameter can be used to indicate where to collect data for training.

[0108] In one embodiment of the present application, after receiving the request sent by the NWDAF entity and generating the model, the method further includes:

[0109] At least one of the following parameters of the model is sent to the NWDAF entity: a model identifier, a model input parameter, a model output parameter, and a model parameter.

[0110] See also Figure 4 , Figure 4 is a schematic diagram of information transmission between multiple functional entities provided by an embodiment of the present invention, Figure 4 It includes four functional entities, namely NRF entity, NWDAF entity, AI training platform 1 (which can be understood as training object 1) and AI training platform 1 (which can be understood as training object 2).

[0111] Step 1a, Training Platform 1 registers with the NRF entity, notifies the NRF entity of the address, location, load, algorithm capability, etc. of Training Platform 1, and the NRF entity returns a response message (Nnrf_NFManagement_NFRegister_request / Rsp) to Training Platform 1. That is, Training Platform 1 (Training Platform) registers its capabilities with NRF, including address, location, load, algorithm capability, algorithm type, etc.

[0112] Step 1b, Training Platform 2 registers with the NRF entity, notifies the NRF entity of the address, location, load, algorithm capability, etc. of Training Platform 2, and the NRF entity returns a response message (Nnrf_NFManagement_NFRegister_request / Rsp) to Training Platform 2. That is, Training Platform 2 (Training Platform) registers its capabilities with NRF, including address, location, load, algorithm capability, algorithm type, and other information.

[0113] Step 2: NWDAF entity triggers data analysis. NWDAF (Inference Platform or Inference Function) triggers data analysis for specific Analytics. There are two cases:

[0114] (a) NF requests NWDAF to report Analytics Data.

[0115] (b) NWDAF itself triggers data analysis to obtain Analytics Data.

[0116] Step 3: The NWDAF entity sends a request message (understood as the first request message) to the NRF entity. The request message includes the algorithm type, NWDAF address, etc., that is, NWDAF applies to NRF for the training platform service, carrying information such as algorithm capability, algorithm type, and NWDAF address.

[0117] Step 4: The NRF entity returns a response message (Nnrf_NFDiscovery_Request response), which includes one or more training platform information, including the training platform address, supported algorithm identifier, algorithm performance, algorithm speed, etc.

[0118] Step 5: NWDAF selects a training platform based on the information returned by NRF. Figure 4 In , the NWDAF entity selects training platform 1 according to the output of the NRF entity.

[0119] Step 6: The NWDAF entity sends a model request to the training platform 1, carrying the algorithm identifier, algorithm performance requirements, and (optional) data address.

[0120] Step 7: The training platform performs data collection and model training.

[0121] Step 8: The training platform responds to the NWDAF entity with a model response, which carries the model identifier, model input (Event ID list), model output, and model parameters.

[0122] Step 9: NWDAF entity completes model deployment.

[0123] Step 10: For case (a) in step 2, NWDAF returns the Analytics Data result to the requesting NF.

[0124] For case (b) in step 2, NWDAF registers with NRF, carrying the Analytic ID and NWDAF address for subsequent NF calls to obtain Analytics Data.

[0125] Figure 4 In the process, the NWDAF entity sends a registration message (Nnrf_NFManagement_NFRegister_Request) to the NRF entity, including: Analytics ID, NWDAF address, and the NRF entity returns a response message to the NWDAF entity.

[0126] In this application, the training platform side (Training Platform) includes:

[0127] Support registering its own capabilities to NRF, including address, location, load, algorithm capability, algorithm type and other information;

[0128] Support data collection and model training based on NWDAF model requests (including algorithm identification, algorithm performance requirements, data address, etc.);

[0129] Supports model response to NWDAF, carrying information such as model identification, model input (Event ID list), model output, model parameters, etc.

[0130] The NWDAF side (Inference Platform or Inference Function) includes:

[0131] Supports applying for training platform services from NRF, carrying information such as algorithm capabilities, algorithm types, and NWDAF addresses;

[0132] Supports selecting a training platform based on the information returned by NRF;

[0133] Supports initiating model requests to the training platform, carrying information such as algorithm identification, algorithm performance requirements, and data address;

[0134] Supports receiving model responses from the training platform, including: model identification, model input (Event ID list), model output, model parameters, etc., and completes model deployment.

[0135] Support Analytics Data reporting requests from NF;

[0136] Supports returning Analytics Data results to the requested NF;

[0137] Support self-triggered data analysis to obtain Analytics Data;

[0138] Supports registering Analytics Data results to NRF, carrying the Analytic ID and NWDAF address.

[0139] The NRF side includes:

[0140] Supports training platform registration-related capabilities, including address, location, load, algorithm capability, algorithm type, and other information;

[0141] Supports returning one or more training platform information to NWDAF, including training platform address, supported algorithm identifier, algorithm performance, algorithm speed, etc.;

[0142] Supports accepting NWDAF registration Analytics Data requests, and supports processing of parameters such as Analytic ID and NWDAF address;

[0143] The network data analysis method of the present application can separate the data training platform and the NWDAF network element. The NWDAF registers capabilities and discovers the training platform through the NRF. In actual deployment, the training platform can use a third-party AI platform or a self-developed AI platform.

[0144] See also Figure 5 , Figure 5 is a schematic diagram of a functional entity provided by an embodiment of the present invention, such as Figure 5 As shown, the first functional entity 500 includes:

[0145] A request module 501 is used to request a first object to generate a model; the first object is a training platform, a training module, a training function entity or a training service module;

[0146] The first receiving module 502 is used to receive the model sent by the first object.

[0147] Furthermore, the request module 501 is used to:

[0148] Sending a first request message to the first object, where the first request message is used to request the first object to generate the model; the model is carried in a first response message;

[0149] or

[0150] Calling a training service provided by a third object for generating the model; the third object is a training module, a training function entity or a training service module.

[0151] Furthermore, the first functional entity 500 also includes:

[0152] A first sending module, configured to send a second request message to a network repository function NRF entity;

[0153] A second receiving module is used to receive a second response message returned by the NRF entity, where the second response message is used to indicate an available second object; the second object is a training platform, a training module, a training function entity or a training service module; and the first object is selected from the second object.

[0154] Furthermore, the second request message carries parameters, and the parameters are used by the NRF entity to determine the second object.

[0155] Furthermore, the second response message carries parameters of the second object, and the parameters of the second object are used by the network data analysis function entity to select the first object from the second objects.

[0156] Furthermore, the first request message includes at least one of the following parameters:

[0157] Algorithm identification parameters, algorithm performance requirement parameters and data address parameters.

[0158] Furthermore, the first response message includes at least one of the following parameters: a model identifier, a model input parameter, a model output parameter, and a model parameter.

[0159] Furthermore, the first functional entity 500 also includes:

[0160] The second sending module is used to send a model registration message to the NRF entity, where the model registration message includes identification information of the model and address information of the network data analysis function NWDAF entity.

[0161] The first functional entity 500 can implement Figure 1 To avoid repetition, the various processes implemented by the network data analysis functional entity in the method embodiment shown will not be described here.

[0162] The first functional entity 500 of the embodiment of the present invention requests a first object to generate a model, the first object being a training platform, a training module, a training functional entity or a training service module, and receives the model sent by the first object. Since the first object and the NWDAF are two separate entities, the first object with a model training function can be used by multiple NWDAFs, thereby improving flexibility.

[0163] See also Figure 6 , Figure 6is a schematic diagram of a functional entity provided by an embodiment of the present invention, such as Figure 6 As shown, the second functional entity 600 includes:

[0164] The first receiving module 601 is used to receive a second request message sent by a network data analysis function NWDAF entity;

[0165] The sending module 602 is used to send a second response message to the NWDAF entity, where the second response message is used to indicate an available second object; the second object is a training platform, a training module, a training function entity or a training service module.

[0166] Furthermore, the second functional entity 600 further includes:

[0167] The first receiving module is used to receive a registration request message sent by the object to be registered; the second object is selected from the objects registered in the network repository function entity NRF.

[0168] Furthermore, the registration request message includes at least one of the following parameters of the object to be registered:

[0169] Address parameters, location parameters, load parameters, algorithm capability parameters, and supported algorithm type parameters.

[0170] Furthermore, the second request message carries parameters, and the parameters are used by the NRF to determine the second object.

[0171] Furthermore, the second response message carries parameters of the second object, and the parameters of the second object are used by the NWDAF to select the first object from the second object.

[0172] Furthermore, the second functional entity 600 further includes:

[0173] The second receiving module is configured to receive a model registration message sent by the NWDAF entity, where the model registration message includes identification information of the model and address information of the NWDAF entity.

[0174] The second functional entity 600 can implement Figure 2 To avoid repetition, the various processes implemented by the network storage repository functional entity in the method embodiment shown will not be described here.

[0175] The second functional entity 600 of the embodiment of the present invention receives a second request message sent by a network data analysis function NWDAF entity; sends a second response message to the NWDAF entity, wherein the second response message is used to indicate an available second object; the second object is a training platform, a training module, a training functional entity, or a training service module. In this way, after obtaining the second object, the NWDAF entity can select the first object from the second object and request the first object to generate a model. Since the first object and the NWDAF are two separate entities, the first object with a model training function can be used by multiple NWDAFs, thereby improving flexibility.

[0176] See also Figure 7 , Figure 7 is a schematic diagram of a functional entity provided by an embodiment of the present invention, such as Figure 7 As shown, the third functional entity 700 is a training object, which includes a training platform, a training module, a training functional entity or a training service module. The third functional entity 700 includes:

[0177] The receiving module 701 is used to receive a request sent by a network data analysis function NWDAF entity and generate a model;

[0178] The first sending module 702 is configured to send the model to the NWDAF entity.

[0179] Furthermore, the receiving module 701 is used for:

[0180] After receiving the first request message sent by the NWDAF entity, data training is performed to generate the model;

[0181] or

[0182] Receive a call request for a data training service sent by the NWDAF entity, and provide a training service for generating the model.

[0183] Furthermore, the third functional entity 700 also includes:

[0184] The second sending module is used to send a registration request message to the network repository function NRF entity, requesting to register with the NRF entity.

[0185] Furthermore, the first request message includes at least one of the following parameters: an algorithm identification parameter, an algorithm performance requirement parameter, and a data address parameter.

[0186] Furthermore, the third functional entity 700 also includes:

[0187] The third sending module is used to send at least one of the following parameters of the model to the NWDAF entity: a model identifier, a model input parameter, a model output parameter, and a model parameter.

[0188] The third functional entity 700 can implement Figure 3 To avoid repetition, the various processes implemented by the training object in the method embodiment shown will not be described here.

[0189] The training object 700 in this embodiment receives a request sent by the network data analysis function NWDAF entity, generates a model, and sends the model to the NWDAF entity. Since the training object has a model training function, and the training object and the NWDAF are two separate entities, the training object with a model training function can be used by multiple NWDAFs, which improves flexibility.

[0190] See also Figure 8 The embodiment of the present invention further provides a functional entity, including a bus 1001, a transceiver 1002, an antenna 1003, a bus interface 1004, a processor 1005 and a memory 1006.

[0191] In one embodiment of the present application, when the functional entity is a network data analysis functional entity, the functional entity includes a processor and a transceiver;

[0192] The transceiver is used to request a first object to generate a model and receive the model sent by the first object, where the first object is a training platform, a training module, a training function entity or a training service module.

[0193] Furthermore, the transceiver is also used for:

[0194] Sending a first request message to the first object, where the first request message is used to request the first object to generate the model; the model is carried in a first response message;

[0195] or

[0196] Calling a training service provided by a third object for generating the model; the third object is a training module, a training function entity or a training service module.

[0197] Furthermore, the transceiver is also used for:

[0198] Sending a second request message to the network repository function NRF entity;

[0199] Receive a second response message returned by the NRF entity, where the second response message is used to indicate an available second object; the second object is a training platform, a training module, a training function entity or a training service module; and the first object is selected from the second object.

[0200] Furthermore, the second request message carries parameters, and the parameters are used by the NRF entity to determine the second object.

[0201] Furthermore, the second response message carries parameters of the second object, and the parameters of the second object are used by the network data analysis function entity to select the first object from the second objects.

[0202] Furthermore, the first request message includes at least one of the following parameters:

[0203] Algorithm identification parameters, algorithm performance requirement parameters and data address parameters.

[0204] Furthermore, the first response message includes at least one of the following parameters: a model identifier, a model input parameter, a model output parameter, and a model parameter.

[0205] Furthermore, the transceiver is also used for:

[0206] A model registration message is sent to the NRF entity, where the model registration message includes identification information of the model and address information of a network data analysis function NWDAF entity.

[0207] In this implementation, the functional entity further includes: a computer program stored in the memory 1006 and executable on the processor 1005. When the computer program is executed by the processor 1005, the following steps may be implemented:

[0208] Requesting a first object to generate a model; the first object is a training platform, a training module, a training function entity or a training service module;

[0209] The model sent by the first object is received.

[0210] Furthermore, the requesting the first object to generate a model specifically includes:

[0211] Sending a first request message to the first object, where the first request message is used to request the first object to generate the model; the model is carried in a first response message;

[0212] or

[0213] Calling a training service provided by a third object for generating the model; the third object is a training module, a training function entity or a training service module.

[0214] Furthermore, when the computer program is executed by the processor 1005, the following steps are also implemented:

[0215] Sending a second request message to the network repository function NRF entity;

[0216] Receive a second response message returned by the NRF entity, where the second response message is used to indicate an available second object; the second object is a training platform, a training module, a training function entity or a training service module; and the first object is selected from the second object.

[0217] Furthermore, the second request message carries parameters, and the parameters are used by the NRF entity to determine the second object.

[0218] Furthermore, the second response message carries parameters of the second object, and the parameters of the second object are used by the network data analysis function entity to select the first object from the second objects.

[0219] Furthermore, the first request message includes at least one of the following parameters:

[0220] Algorithm identification parameters, algorithm performance requirement parameters and data address parameters.

[0221] Furthermore, the first response message includes at least one of the following parameters: a model identifier, a model input parameter, a model output parameter, and a model parameter.

[0222] Furthermore, when the computer program is executed by the processor 1005, the following steps are also implemented:

[0223] A model registration message is sent to the NRF entity, where the model registration message includes identification information of the model and address information of a network data analysis function NWDAF entity.

[0224] Functional entities can achieve Figure 1 To avoid repetition, the various processes implemented by the network data analysis functional entity in the method embodiment shown will not be described here.

[0225] The functional entity of this embodiment requests the first object to generate a model, the first object is a training platform, a training module, a training functional entity or a training service module, and receives the model sent by the first object. Since the first object and the NWDAF are two separate entities, the first object with the model training function can be used by multiple NWDAFs, which improves flexibility.

[0226] In one embodiment of the present application, when the functional entity is a network repository functional entity, the functional entity includes a processor and a transceiver;

[0227] The transceiver is used to receive a second request message sent by a network data analysis function NWDAF entity; send a second response message to the NWDAF entity, and the second response message is used to indicate an available second object; the second object is a training platform, a training module, a training function entity or a training service module.

[0228] Furthermore, the transceiver is also used for:

[0229] A registration request message is received from an object to be registered; and the second object is selected from objects registered in the network repository function entity NRF.

[0230] Furthermore, the registration request message includes at least one of the following parameters of the object to be registered:

[0231] Address parameters, location parameters, load parameters, algorithm capability parameters, and supported algorithm type parameters.

[0232] Furthermore, the second request message carries parameters, and the parameters are used by the NRF to determine the second object.

[0233] Furthermore, the second response message carries parameters of the second object, and the parameters of the second object are used by the NWDAF to select the first object from the second object.

[0234] Furthermore, the transceiver is also used for:

[0235] A model registration message sent by the NWDAF entity is received, where the model registration message includes identification information of the model and address information of the NWDAF entity.

[0236] In this implementation, the functional entity further includes: a computer program stored in the memory 1006 and executable on the processor 1005. When the computer program is executed by the processor 1005, the following steps may be implemented:

[0237] Receiving a second request message sent by a network data analysis function NWDAF entity;

[0238] A second response message is sent to the NWDAF entity, where the second response message is used to indicate an available second object; the second object is a training platform, a training module, a training function entity or a training service module.

[0239] Furthermore, when the computer program is executed by the processor 1005, the following steps are also implemented:

[0240] A registration request message is received from an object to be registered; and the second object is selected from objects registered in the network repository function entity NRF.

[0241] Furthermore, the registration request message includes at least one of the following parameters of the object to be registered:

[0242] Address parameters, location parameters, load parameters, algorithm capability parameters, and supported algorithm type parameters.

[0243] Furthermore, the second request message carries parameters, and the parameters are used by the NRF to determine the second object.

[0244] Furthermore, the second response message carries parameters of the second object, and the parameters of the second object are used by the NWDAF to select the first object from the second object.

[0245] Furthermore, when the computer program is executed by the processor 1005, the following steps are also implemented:

[0246] A model registration message sent by the NWDAF entity is received, where the model registration message includes identification information of the model and address information of the NWDAF entity.

[0247] Functional entities can achieve Figure 2 To avoid repetition, the various processes implemented by the network storage repository functional entity in the method embodiment shown will not be described here.

[0248] The functional entity of this embodiment receives a second request message sent by a network data analysis function NWDAF entity; sends a second response message to the NWDAF entity, where the second response message is used to indicate an available second object; the second object is a training platform, a training module, a training function entity, or a training service module. In this way, after obtaining the second object, the NWDAF entity can select the first object from the second object and request the first object to generate a model. Since the first object and the NWDAF are two separate entities, the first object with a model training function can be used by multiple NWDAFs, which improves flexibility.

[0249] In one embodiment of the present application, the functional entity is a training object, and when the training object includes a training platform, a training module, a training functional entity or a training service module, the functional entity includes a processor and a transceiver:

[0250] The transceiver is used to receive a request sent by a network data analysis function NWDAF entity, generate a model, and send the model to the NWDAF entity.

[0251] Furthermore, the transceiver is also used for:

[0252] After receiving the first request message sent by the NWDAF entity, data training is performed to generate the model;

[0253] or

[0254] Receive a call request for a data training service sent by the NWDAF entity, and provide a training service for generating the model.

[0255] Furthermore, the transceiver is also used for:

[0256] Send a registration request message to the network repository function NRF entity, requesting to register with the NRF entity.

[0257] Furthermore, the first request message includes at least one of the following parameters: an algorithm identification parameter, an algorithm performance requirement parameter, and a data address parameter.

[0258] Furthermore, the transceiver is also used for:

[0259] At least one of the following parameters of the model is sent to the NWDAF entity: a model identifier, a model input parameter, a model output parameter, and a model parameter.

[0260] In this implementation, the functional entity further includes: a computer program stored in the memory 1006 and executable on the processor 1005. When the computer program is executed by the processor 1005, the following steps may be implemented:

[0261] Receive requests sent by the network data analysis function NWDAF entity and generate models;

[0262] The model is sent to the NWDAF entity.

[0263] Furthermore, when the computer program is executed by the processor 1005, the following steps are also implemented: after receiving the first request message sent by the NWDAF entity, data training is performed to generate the model;

[0264] or

[0265] Receive a call request for a data training service sent by the NWDAF entity, and provide a training service for generating the model.

[0266] Furthermore, when the computer program is executed by the processor 1005, the following steps are also implemented: sending a registration request message to a network repository function NRF entity, requesting to register with the NRF entity.

[0267] Furthermore, the first request message includes at least one of the following parameters: an algorithm identification parameter, an algorithm performance requirement parameter, and a data address parameter.

[0268] Furthermore, when the computer program is executed by the processor 1005, the following steps are also implemented: sending at least one of the following parameters of the model to the NWDAF entity: a model identifier, a model input parameter, a model output parameter, and a model parameter.

[0269] Functional entities can achieve Figure 3 To avoid repetition, the various processes implemented by the training object in the method embodiment shown will not be described here.

[0270] The functional entity of the embodiment of the present invention receives a request sent by a network data analysis function NWDAF entity, generates a model, and sends the model to the NWDAF entity. Since the training object has a model training function, and the training object and the NWDAF are two separate entities, the training object with the model training function can be used by multiple NWDAFs, which improves flexibility.

[0271] exist Figure 8 In the embodiment, the bus architecture (represented by bus 1001) may include any number of interconnected buses and bridges, and bus 1001 links various circuits including one or more processors represented by processor 1005 and memory represented by memory 1006. Bus 1001 may also link various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. Bus interface 1004 provides an interface between bus 1001 and transceiver 1002. Transceiver 1002 may be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. Data processed by processor 1005 is transmitted on a wireless medium via antenna 1003, and further, antenna 1003 also receives data and transmits the data to processor 1005.

[0272] The processor 1005 is responsible for managing the bus 1001 and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management and other control functions. The memory 1006 can be used to store data used by the processor 1005 when performing operations.

[0273] Optionally, the processor 1005 may be a CPU, an ASIC, an FPGA or a CPLD.

[0274] Preferably, an embodiment of the present invention further provides an electronic device, comprising a processor 1005, a memory 1006, and a computer program stored in the memory 1006 and executable on the processor 1005, wherein the computer program is executed by the processor 1005 to implement the above Figure 1-Figure 3The various processes of any one of the network data analysis method embodiments can achieve the same technical effect, and will not be repeated here to avoid repetition.

[0275] The embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, which implements the above-mentioned Figure 1-Figure 3 The various processes of any of the network data analysis method embodiments shown in the figure can achieve the same technical effect. To avoid repetition, they will not be described again here.

[0276] The computer-readable storage medium is, for example, a ROM, RAM, a magnetic disk or an optical disk.

[0277] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0278] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0279] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

Claims

1. A network data analysis method, used in a network data analysis functional entity, characterized in that: The network data analysis method comprises: Requesting a first object to generate a model; the first object is a training platform, a training module, a training function entity or a training service module; receiving the model sent by the first object; Before requesting the first object to generate a model, the method further includes: Sending a second request message to the network repository function NRF entity; receiving a second response message returned by the NRF entity, where the second response message is used to indicate an available second object; the second object is a training platform, a training module, a training function entity or a training service module; and the first object is selected from the second object; The requesting the first object to generate a model is specifically: Sending a first request message to the first object, where the first request message is used to request the first object to generate the model; the model is carried in a first response message; or Calling a training service provided by a third object for generating the model; the third object is a training module, a training function entity or a training service module.

2. The network data analysis method according to claim 1, characterized in that: The second request message carries parameters, and the parameters are used by the NRF entity to determine the second object.

3. The network data analysis method according to claim 1, characterized in that: The second response message carries parameters of the second object, and the parameters of the second object are used by the network data analysis function entity to select the first object from the second objects.

4. The network data analysis method according to claim 1, characterized in that: The first request message includes at least one of the following parameters: Algorithm identification parameters, algorithm performance requirement parameters and data address parameters.

5. The network data analysis method according to claim 1, characterized in that: The first response message includes at least one of the following parameters: a model identifier, a model input parameter, a model output parameter, and a model parameter.

6. The network data analysis method according to any one of claims 1 to 3, characterized in that: After receiving the model sent by the first object, the method further includes: A model registration message is sent to the NRF entity, where the model registration message includes identification information of the model and address information of a network data analysis function NWDAF entity.

7. A network data analysis method for a network storage repository functional entity, characterized in that: The network data analysis method comprises: Receiving a second request message sent by a network data analysis function NWDAF entity; Sending a second response message to the NWDAF entity, where the second response message is used to indicate an available second object; the second object is a training platform, a training module, a training function entity, or a training service module; The second object is used to select the first object, the first object generates a model in response to a request from the network data analysis function NWDAF entity; the first object is a training platform, a training module, a training function entity or a training service module, and the model is sent to the network data analysis function NWDAF; The first object generates a model in response to a request from the network data analysis function NWDAF entity: The network data analysis function NWDAF entity sends a first request message to the first object, where the first request message is used to request the first object to generate the model; the model is carried by a first response message; or The network data analysis function NWDAF entity calls a training service provided by a third object for generating the model; the third object is a training module, a training function entity or a training service module.

8. The network data analysis method according to claim 7, characterized in that: Before the receiving the second request message sent by the network data analysis function NWDAF entity, the method further includes: A registration request message is received from an object to be registered; the second object is selected from objects registered in the network repository function entity NRF.

9. The network data analysis method according to claim 8, characterized in that: The registration request message includes at least one of the following parameters of the object to be registered: Address parameters, location parameters, load parameters, algorithm capability parameters, and supported algorithm type parameters.

10. The network data analysis method according to any one of claims 7 to 9, characterized in that: The second request message carries parameters, and the parameters are used by the NRF to determine the second object.

11. The network data analysis method according to any one of claims 7 to 9, characterized in that: The second response message carries parameters of the second object, and the parameters of the second object are used by the NWDAF to select the first object from the second object.

12. The network data analysis method according to any one of claims 7 to 9, characterized in that: After sending the second response message to the NWDAF entity, the method further includes: A model registration message sent by the NWDAF entity is received, where the model registration message includes identification information of the model and address information of the NWDAF entity.

13. A network data analysis method for a training object, wherein the training object comprises a training platform, a training module, a training function entity or a training service module, characterized in that: The network data analysis method comprises: Receive requests sent by the network data analysis function NWDAF entity and generate models; Sending the model to the NWDAF entity; The receiving request sent by the network data analysis function NWDAF entity generates a model specifically as follows: After receiving the first request message sent by the NWDAF entity, data training is performed to generate the model; or Receive a call request for a data training service sent by the NWDAF entity, and provide a training service for generating the model.

14. The network data analysis method according to claim 13, characterized in that: The receiving a request sent by the network data analysis function NWDAF entity, before generating the model, also includes: Send a registration request message to the network repository function NRF entity, requesting to register with the NRF entity.

15. The network data analysis method according to claim 13 or 14, characterized in that: The first request message includes at least one of the following parameters: an algorithm identification parameter, an algorithm performance requirement parameter, and a data address parameter.

16. The network data analysis method according to claim 13 or 14, characterized in that: After receiving the request sent by the network data analysis function NWDAF entity and generating the model, the method further includes: At least one of the following parameters of the model is sent to the NWDAF entity: a model identifier, a model input parameter, a model output parameter, and a model parameter.

17. A functional entity, the functional entity being a network data analysis functional entity, characterized in that: The functional entity includes a processor and a transceiver; The transceiver is used to request a first object to generate a model and receive the model sent by the first object, wherein the first object is a training platform, a training module, a training function entity or a training service module; The transceiver is also used for: Sending a second request message to the network repository function NRF entity; receiving a second response message returned by the NRF entity, where the second response message is used to indicate an available second object; the second object is a training platform, a training module, a training function entity or a training service module; and the first object is selected from the second object; The transceiver is also used for: Sending a first request message to the first object, where the first request message is used to request the first object to generate the model; the model is carried in a first response message; or Calling a training service provided by a third object for generating the model; the third object is a training module, a training function entity or a training service module.

18. The functional entity according to claim 17, characterized in that The second request message carries parameters, and the parameters are used by the NRF entity to determine the second object.

19. The functional entity according to claim 17, characterized in that The second response message carries parameters of the second object, and the parameters of the second object are used by the network data analysis function entity to select the first object from the second objects.

20. The functional entity according to claim 17, characterized in that The first request message includes at least one of the following parameters: Algorithm identification parameters, algorithm performance requirement parameters and data address parameters.

21. The functional entity according to claim 17, characterized in that The first response message includes at least one of the following parameters: a model identifier, a model input parameter, a model output parameter, and a model parameter.

22. The functional entity according to any one of claims 17 to 19, characterized in that: The transceiver is also used for: A model registration message is sent to the NRF entity, where the model registration message includes identification information of the model and address information of a network data analysis function NWDAF entity.

23. A functional entity, the functional entity being a network storage repository functional entity, characterized in that: The functional entity includes a processor and a transceiver; The transceiver is used to receive a second request message sent by a network data analysis function NWDAF entity; send a second response message to the NWDAF entity, where the second response message is used to indicate an available second object; the second object is a training platform, a training module, a training function entity or a training service module; The second object is used to select the first object, the first object generates a model in response to a request from the network data analysis function NWDAF entity; the first object is a training platform, a training module, a training function entity or a training service module, and the model is sent to the network data analysis function NWDAF; The first object generates a model in response to a request from the network data analysis function NWDAF entity: The network data analysis function NWDAF entity sends a first request message to the first object, where the first request message is used to request the first object to generate the model; the model is carried by a first response message; or The network data analysis function NWDAF entity calls a training service provided by a third object for generating the model; the third object is a training module, a training function entity or a training service module.

24. The functional entity according to claim 23, characterized in that The transceiver is also used for: A registration request message is received from an object to be registered; the second object is selected from objects registered in the network repository function entity NRF.

25. The functional entity according to claim 24, characterized in that The registration request message includes at least one of the following parameters of the object to be registered: Address parameters, location parameters, load parameters, algorithm capability parameters, and supported algorithm type parameters.

26. The functional entity according to any one of claims 23 to 25, characterized in that The second request message carries parameters, and the parameters are used by the NRF to determine the second object.

27. The functional entity according to any one of claims 23 to 25, characterized in that The second response message carries parameters of the second object, and the parameters of the second object are used by the NWDAF to select the first object from the second object.

28. The functional entity according to any one of claims 23 to 25, characterized in that The transceiver is also used for: A model registration message sent by the NWDAF entity is received, where the model registration message includes identification information of the model and address information of the NWDAF entity.

29. A functional entity, the functional entity is a training object, the training object includes a training platform, a training module, a training functional entity or a training service module, characterized in that: The functional entity includes a processor and a transceiver: The transceiver is used to receive a request sent by a network data analysis function NWDAF entity, generate a model, and send the model to the NWDAF entity; The transceiver is further used for: After receiving the first request message sent by the NWDAF entity, data training is performed to generate the model; or Receive a call request for a data training service sent by the NWDAF entity, and provide a training service for generating the model.

30. The functional entity according to claim 29, characterized in that The transceiver is further used for: Send a registration request message to the network repository function NRF entity, requesting to register with the NRF entity.

31. The functional entity according to claim 29, characterized in that The first request message includes at least one of the following parameters: an algorithm identification parameter, an algorithm performance requirement parameter, and a data address parameter.

32. The functional entity according to claim 29, characterized in that The transceiver is further used for: At least one of the following parameters of the model is sent to the NWDAF entity: a model identifier, a model input parameter, a model output parameter, and a model parameter.

33. A functional entity, the functional entity being a network data analysis functional entity, characterized in that: The functional entities include: A request module, used for requesting a first object to generate a model; the first object is a training platform, a training module, a training function entity or a training service module; A receiving module, used for receiving the model sent by the first object; A first sending module, configured to send a second request message to a network repository function NRF entity; A second receiving module is used to receive a second response message returned by the NRF entity, where the second response message is used to indicate an available second object; the second object is a training platform, a training module, a training function entity or a training service module; and the first object is selected from the second object; The request module is specifically used for: Sending a first request message to the first object, where the first request message is used to request the first object to generate the model; the model is carried in a first response message; or Calling a training service provided by a third object for generating the model; the third object is a training module, a training function entity or a training service module.

34. A functional entity, the functional entity being a network storage library functional entity, characterized in that: The functional entities include: A receiving module, configured to receive a second request message sent by a network data analysis function NWDAF entity; A sending module, configured to send a second response message to the NWDAF entity, where the second response message is used to indicate an available second object; the second object is a training platform, a training module, a training function entity or a training service module; The second object is used to select the first object, the first object generates a model in response to a request from the network data analysis function NWDAF entity; the first object is a training platform, a training module, a training function entity or a training service module, and the model is sent to the network data analysis function NWDAF; The first object generates a model in response to a request from the network data analysis function NWDAF entity: The network data analysis function NWDAF entity sends a first request message to the first object, where the first request message is used to request the first object to generate the model; the model is carried by a first response message; or The network data analysis function NWDAF entity calls a training service provided by a third object for generating the model; the third object is a training module, a training function entity or a training service module.

35. A functional entity, wherein the functional entity is a training object, wherein the training object comprises a training platform, a training module, a training functional entity or a training service module, wherein: The functional entities include: A receiving module, used to receive a request sent by a network data analysis function NWDAF entity and generate a model; A sending module, used for sending the model to the NWDAF entity; The receiving module is specifically used for: After receiving the first request message sent by the NWDAF entity, data training is performed to generate the model; or Receive a call request for a data training service sent by the NWDAF entity, and provide a training service for generating the model.

36. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the network data analysis method as claimed in any one of claims 1 to 6, or, when executed by the processor, implements the steps of the network data analysis method as claimed in any one of claims 7 to 12, or, when executed by the processor, implements the steps of the network data analysis method as claimed in any one of claims 13 to 16.

37. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the network data analysis method as described in any one of claims 1 to 6, or, when executed by the processor, implements the steps of the network data analysis method as described in any one of claims 7 to 12, or, when executed by the processor, implements the steps of the network data analysis method as described in any one of claims 13 to 16.

Images