Network entity for determining a model for digitally analyzing input data
The disclosure relates to a network entity for determining at least one model parameter of a model for digitally analyzing input data depending on the at least one model parameter of a model, the network entity being configured to receive a model request from a requesting entity over the communication network, the model request requesting the at least one model parameter of the model, to obtain the requested at least one model parameter by at least one of the following: executing a machine-learning model training algorithm, the machine-learning model training algorithm being configured to train the model with input data in order to determine at least one of the requested model parameter; searching a local data base for an existing model; or requesting the at least one model parameter from a further network entity; and to send the requested model parameter towards the requesting entity over the communication network.
1 . A method for determining at least one model parameter of a model for digitally analyzing input data depending on the at least one model parameter of the model, the method comprising:
receiving, by a network entity of a public mobile land mobile network (PLMN) implementing a 5G core (5GC), a model request from a network data analytics function (NWDAF), wherein the model request is provided with area of interest information and/or Network Slice Selection Assistance Information (NSSAI), and wherein the network entity implements a machine learning (ML) model training platform which supports joint training of data sets from different parties without disclosure of the data sets between the different parties, and wherein the NWDAF implements an ML model inference platform; and
in response to the model request, sending, by the network entity, a model parameter or a model towards the NWDAF.
2 . The method of claim 1 , further comprising:
registering a respective model at a network function (NF) repository function (NRF) of the PLMN based on a respective registration signal comprising registration information for the respective model.
3 . The method of claim 2 , wherein the registration information comprises at least one of the following: information on a model type, a data analytics identification, a set of features or event identifications (IDs) of the model, or at least one model parameter of the model.
4 . The method of claim 1 , wherein the model request is received with at least one of the following information:
a model type,
a machine-leaning training algorithm,
an analytics identification (ID),
feature sets,
an input data type particular event ID,
an application ID,
a model ID, or
a model time.
5 . The method of claim 1 , further comprising:
executing and/or providing a machine-learning model training algorithm from a set of machine-learning model training algorithms available at the network entity.
6 . The method of claim 1 , wherein the area of interest information comprises one or more tracking area IDs (TAIs).
7 . The method of claim 1 , further comprising:
obtaining, by the network entity, at least one model parameter, wherein obtaining the at least one model parameter comprises at least one of the following:
executing a machine-learning model training algorithm to train the model with input data in order to determine the at least one model parameter;
searching a local database for an existing model; or
requesting the at least one model parameter from a further network entity.
8 . A method for determining at least one model parameter of a model for digitally analyzing input data depending on the at least one model parameter of the model, the method comprising:
receiving, by a network entity of a public mobile land mobile network (PLMN) implementing a 5G core (5GC), a model request from a network data analytics function (NWDAF), wherein the model request is provided with area of interest information and/or Network Slice Selection Assistance Information (NSSAI), and wherein the network entity implements an artificial intelligence (AI) model training platform which supports joint training of data sets from different parties without disclosure of the data sets between the different parties, and wherein the NWDAF implements an AI model inference platform; and
in response to the model request, sending, by the network entity, a model parameter or a model towards the NWDAF.
9 . The method of claim 8 , further comprising:
registering a respective model at a network function (NF) repository function (NRF) of the PLMN based on a respective registration signal comprising registration information for the respective model.
10 . The method of claim 9 , wherein the registration information comprises at least one of the following: information on a model type, a data analytics identification, a set of features or event identifications (IDs) of the model, or at least one model parameter of the model.
11 . The method of claim 8 , wherein the model request is received with at least one of the following information:
a model type,
a machine-leaning training algorithm,
an analytics identification (ID),
feature sets,
an input data type particular event ID,
an application ID,
a model ID, or
a model time.
12 . The method of claim 8 , further comprising:
executing and/or providing a machine-learning model training algorithm from a set of machine-learning model training algorithms available at the network entity.
13 . The method of claim 8 , wherein the area of interest information comprises one or more tracking area IDs (TAIs).
14 . The method of claim 8 , further comprising:
obtaining, by the network entity, at least one model parameter, wherein obtaining the at least one model parameter comprises at least one of the following:
executing a machine-learning model training algorithm to train the model with input data in order to determine the at least one model parameter;
searching a local database for an existing model; or
requesting the at least one model parameter from a further network entity.
15 . A non-transitory computer-readable storage medium having processor-executable instructions stored thereon for determining at least one model parameter of a model for digitally analyzing input data depending on the at least one model parameter of the model, wherein the processor-executable instructions, when executed, facilitate performance of the following:
receiving, by a network entity of a public mobile land mobile network (PLMN) implementing a 5G core (5GC), a model request from a network data analytics function (NWDAF), wherein the model request is provided with area of interest information and/or Network Slice Selection Assistance Information (NSSAI), and wherein the network entity implements an artificial intelligence (AI) model training platform which supports joint training of data sets from different parties without disclosure of the data sets between the different parties, and wherein the NWDAF implements an AI model inference platform; and
in response to the model request, sending, by the network entity, a model parameter or a model towards the NWDAF.
16 . The non-transitory computer-readable storage medium of claim 15 , wherein the processor-executable instructions, when executed, further facilitate performance of the following:
registering a respective model at a network function (NF) repository function (NRF) of the PLMN based on a respective registration signal comprising registration information for the respective model.
17 . The non-transitory computer-readable storage medium of claim 16 , wherein the registration information comprises at least one of the following: information on a model type, a data analytics identification, a set of features or event identifications (IDs) of the model, or at least one model parameter of the model.
18 . The non-transitory computer-readable storage medium of claim 15 , wherein the model request is received with at least one of the following information:
a model type,
a machine-leaning training algorithm,
an analytics identification (ID),
feature sets,
an input data type particular event ID,
an application ID,
a model ID, or
a model time.
19 . The non-transitory computer-readable storage medium of claim 15 , wherein the processor-executable instructions, when executed, further facilitate performance of the following:
executing and/or providing a machine-learning model training algorithm from a set of machine-learning model training algorithms available at the network entity.
20 . The non-transitory computer-readable storage medium of claim 15 , wherein the area of interest information comprises one or more tracking area IDs (TAIs).