Network data analysis method, functional entity and electronic device
A network data analysis method, a functional entity and an electronic device, the network data analysis method comprising: requesting that a first object generate a first model ( 101 ), the first object being a training platform, a training module, a training functional entity or a training service module; receiving a model sent by the first object ( 102 ).
1 . A network data analysis method, applied to a network data analytics function (NWDAF) entity, the network data analysis method comprising:
requesting 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
receiving model information of the model sent by the first object,
wherein before the requesting the first object to generate the model, the method further comprises:
sending a second request message to a network repository function (NRF) entity; and
receiving a second response message which is returned by the NRF entity, the second response message being used to indicate available second objects; each of the second objects being the training platform, the training module, the training functional entity, or the training service module; the first object being selected from the second objects.
2 . The network data analysis method of claim 1 , wherein the requesting the first object to generate the model specifically comprises:
sending, to the first object, a first request message for requesting the first object to generate the model; the model information being carried by a first response message; or
invoking a training service provided by the first object to generate the model; the first object being the training module, the training functional entity, or the training service module.
3 . The network data analysis method of claim 2 , wherein the first request message comprises at least one of an algorithm identifier parameter, an algorithm performance requirement parameter, or a data address parameter, and the first response message comprises at least one of an identifier, an input parameter, an output parameter, or other model parameters of the model.
4 . The network data analysis method of claim 2 , wherein after the receiving the model information sent by the first object, the method further comprises:
sending, to the NRF entity, a model registration message, the model registration message comprising identifier information of the model and address information of the NWDAF entity.
5 . The network data analysis method of claim 1 , wherein the second request message carries parameters used by the NRF entity to determine the second objects.
6 . The network data analysis method of claim 1 , wherein the second response message carries parameters of the second objects, the parameters are used by the NWDAF entity to select the first object from the second objects.
7 . A functional entity, configured as a network data analytics function (NWDAF) entity, the functional entity comprising a processor and a transceiver,
the transceiver configured to cooperate with the processor to perform the method according to claim 1 .
8 . A network data analysis method, applied to a training object, the training object comprising a training platform, a training module, a training functional entity, or a training service module, the network data analysis method comprising:
receiving a request sent by a network data analytics function (NWDAF) entity and generating a model; and
sending model information of the model to the NWDAF entity,
wherein before the receiving the request sent by the NWDAF entity and generating the model, the network data analysis method further comprises:
sending a registration request message to a network repository function NRF) entity, to request registration with the NRF entity,
wherein after the receiving the request sent by the NWDAF entity and generating the model, the network data analysis method further comprises:
sending, to the NWDAF entity, at least one of: an identifier, an input parameter, an output parameter, or parameters of the model.
9 . The network data analysis method of claim 8 , wherein the receiving the request sent by the NWDAF entity and generating the model specifically comprises:
receiving a first request message sent by the NWDAF entity, and performing data training to generate the model; or
receiving a request of invoking data training service sent by the NWDAF entity, to provide a training service for generating the model.
10 . The network data analysis method of claim 9 , wherein the first request message comprises at least one of an algorithm identifier parameter, an algorithm performance requirement parameter, or a data address parameter.
11 . A functional entity, configured as a training object comprising a training platform, a training module, a training functional entity, or a training service module, the functional entity comprising a processor and a transceiver,
the transceiver is configured to cooperate with the processor to perform the method according to claim 8 .