Methods, apparatus and machine-readable media relating to data analytics in a communications network

1 . A method performed by a first data analytics entity for a communications network, the first data analytics entity having access to a first dataset of network data, the method comprising:

receiving a request message from a second data analytics entity for the communications network, the request message comprising a model generated by the second data analytics entity using a machine-learning algorithm based on a second dataset to which the second data analytics entity has access, and an indication of an analytic to be calculated by the model;

applying the model to the first dataset to measure an accuracy of the model; and

transmitting a response message to the second data analytics entity comprising an indication of the accuracy of the model when applied to the first dataset.

2 . The method according to claim 1 , wherein the request message further comprises an indication of the machine-learning algorithm used by the second data analytics entity.

3 . The method according to claim 1 , further comprising transmitting a registration request message to a network function repository entity, the registration request message comprising one or more of: a data profile for the first dataset; an indication of analytics which the first data analytics entity is capable of calculating; and an indication that the first data analytics entity is capable of responding to request messages from other data analytics entities.

4 . The method according to claim 3 , wherein the data profile for the first dataset comprises one or more of: an identifier of the first dataset; a number of data samples in the first dataset; and information relating to parameters of the first dataset.

5 . The method according to claim 1 , further comprising, responsive to a determination that the accuracy of the model when applied to the first dataset is greater than an accuracy of a local model utilized by the first data analytics entity to calculate the analytic, replacing the local model with the model contained in the request message.

6 . The method according to claim 1 , further comprising, responsive to a determination that the accuracy of the model when applied to the first dataset is greater than an accuracy of a local model utilized by the first data analytics entity to calculate the analytic, combining the local model with the model contained in the request message to generate a new local model.

7 . The method according to claim 1 , wherein at least one of the first data analytics entity and the second data analytics entity implements functionality of one or more of: a Network Data Analytics Function, NWDAF; and a Management and Organization Data Analytics Function, MDAF.

8 . A method performed by a second data analytics entity for a communications network, the second data analytics entity having access to a second dataset of network data, the method comprising:

transmitting a request message to a first data analytics entity for the communications network, the request message comprising a model generated by the second data analytics entity using a machine-learning algorithm based on the second dataset, and an indication of an analytic to be calculated by the model, the first data analytics entity having access to a first dataset of the network data; and

receiving a response message from the first data analytics entity comprising an indication of an accuracy of the model when applied to the first dataset to calculate one or more values for the analytic.

9 . The method according to claim 8 , wherein the request message further comprises an indication of the machine-learning algorithm used by the second data analytics entity.

10 . A first data analytics entity for a communications network, the first data analytics entity having access to a first dataset of network data and comprising processing circuitry and a non-transitory machine-readable medium storing instructions which, when executed by the processing circuitry, cause the first data analytics entity to:

receive a request message from a second data analytics entity for the communications network, the request message comprising a model generated by the second data analytics entity using a machine-learning algorithm based on a second dataset to which the second data analytics entity has access, and an indication of an analytic to be calculated by the model;

apply the model to the first dataset to measure an accuracy of the model; and

transmit a response message to the second data analytics entity comprising an indication of the accuracy of the model when applied to the first dataset.

11 . The first data analytics entity according to claim 10 , wherein the first data analytics entity is further caused to transmit a registration request message to a network function repository entity, the registration request message comprising one or more of: a data profile for the first dataset; an indication of analytics which the first data analytics entity is capable of calculating; and an indication that the first data analytics entity is capable of responding to request messages from other data analytics entities.

12 . The first data analytics entity according to claim 11 , wherein the data profile for the first dataset comprises one or more of: an identifier of the first dataset; a number of data samples in the first dataset; and information relating to parameters of the first dataset.

13 . The first data analytics entity according to claim 10 , wherein the first data analytics entity is further caused to, responsive to a determination that the accuracy of the model when applied to the first dataset is greater than an accuracy of a local model utilized by the first data analytics entity to calculate the analytic, replace the local model with the model contained in the request message or combine the local model with the model contained in the request message to generate a new local model.

14 . A second data analytics entity for a communications network, the second data analytics entity having access to a second dataset of network data and comprising processing circuitry and a non-transitory machine-readable medium storing instructions which, when executed by the processing circuitry, cause the second data analytics entity to:

transmit a request message to a first data analytics entity for the communications network, the request message comprising a model generated by the second data analytics entity using a machine-learning algorithm based on the second dataset, and an indication of an analytic to be calculated by the model, the first data analytics entity having access to a first dataset of the network data; and

receive a response message from the first data analytics entity comprising an indication of an accuracy of the model when applied to the first dataset to calculate one or more values for the analytic.

15 . The second data analytics entity according to claim 14 , wherein the second data analytics entity is further caused to:

transmit a dataset request message to a network function repository entity, the dataset request message comprising an indication of one or more conditions for a dataset; and

receive a dataset response message from the network function repository entity, the dataset response message comprising an indication of one or more candidate datasets, including the first dataset, meeting the one or more conditions.

16 . The second data analytics entity according to claim 15 , wherein the dataset request message comprises a dataset subscription message, subscribing to receive indications of datasets from the network function repository entity, and wherein the dataset response message comprises a dataset service message in response to the subscription.

17 . The second data analytics entity according to claim 15 , wherein the second data analytics entity is further caused to:

transmit a data analytic request message to the network function repository entity, the data analytic request message comprising an indication of at least one of the one or more candidate datasets; and

receive a data analytic response message from the network function repository entity, the data analytic response message comprising an indication of one or more candidate data analytics entities, including the first data analytics entity, having access to the at least one of the one or more candidate datasets.