Devices and methods for predicting a mobile network experience
The present disclosure relates to a device for predicting a mobile network experience. In an inference phase, the device obtains network Key Performance Indicator (KPI) data for the mobile network by executing a set of test procedures using a mobile application on a mobile device in the mobile network, obtains a trained machine learning model and feeds it with the network KPI data, and estimates, using the trained machine learning model, a network experience score for the mobile application based on the network KPI data. The disclosure also presents a device that, in a training phase, obtains training data, calculates a set of network experience scores for a mobile application, based on the training data, obtains network KPI data for the mobile network, and generates a database comprising the set of network experience scores of the mobile application.
1 . A device for predicting a mobile network experience, the device comprising:
one or more processors and a non-volatile memory connected to the one or more processors, the non-volatile memory storing executable code which, when executed by the one or more processors, causes the device to
obtain network Key Performance Indicator, KPI, data for the mobile network by executing a set of test procedures using one or more mobile applications on one or more mobile devices in the mobile network;
obtain a first trained machine learning model and a second trained machine learning model for each mobile service of the one or more mobile applications, wherein the first trained machine learning model is based on a regression model and the second trained machine learning model is based on a classification model;
feed the first and second trained machine learning models with the network KPI data; and
estimate, based on the network KPI data and using the first trained machine learning model, a network experience score for at least one mobile application from the one or more mobile applications, and estimate, based on the network KPI data and using the second trained machine learning model, a network experience grade for the at least one mobile application in order to represent a network performance as experienced by a user.
2 . The device according to claim 1 , wherein:
the at least one mobile application is based on an encrypted protocol and provides an event that is not accessible to the device.
3 . A method for predicting a mobile network experience, the method comprising:
in an inference phase:
obtaining network Key Performance Indicator, KPI, data for a mobile network by executing a set of test procedures using one or more mobile applications on one or more mobile devices in the mobile network;
obtaining a first trained machine learning model and a second trained machine learning model for each mobile service of the one or more mobile applications, wherein the first trained machine learning model is based on a regression model and the second trained machine learning model is based on a classification model;
feeding the first and second trained machine learning models it with the network KPI data; and
estimating, by the first trained machine learning model and based on the network KPI data, a network experience score for at least one mobile application from the one or more mobile applications, and estimate, based on the network KPI data and using the second trained machine learning model, a network experience grade for the at least one mobile application in order to represent a network performance as experienced by a user.
4 . The method according to claim 3 , wherein:
the at least one mobile application is based on an encrypted protocol and provides an event that is not accessible.
5 . The method according to claim 3 , wherein the network experience score has a non-negative integer value.
6 . The method according to claim 3 , wherein
the network experience grade is an outstanding grade, a very good grade, a good grade, a satisfactory grade, or a sufficient grade.
7 . The device according to claim 1 , wherein the network experience score has a non-negative integer value.
8 . The device according to claim 1 , wherein
the network experience grade is an outstanding grade, a very good grade, a good grade, a satisfactory grade, or a sufficient grade.
9 . A non-transitory storage medium comprising:
executable program code which, when executed by a processor, causes the processor to obtain network Key Performance Indicator, KPI, data for a mobile network by executing a set of test procedures using one or more mobile applications on one or more mobile devices in the mobile network;
obtain a first trained machine learning model and a second trained machine learning model for each mobile service of the one or more mobile applications, wherein the first trained machine learning model is based on a regression model and the second trained machine learning model is based on a classification model;
feed the first and second trained machine learning models with the network KPI data; and
estimate, by the first trained machine learning model and based on the network KPI data, a network experience score for at least one mobile application from the one or more mobile applications, and estimate, based on the network KPI data and using the second trained machine learning model, a network experience grade for the at least one mobile application in order to represent a network performance as experienced by a user.
10 . The non-transitory storage medium of claim 9 wherein the at least one mobile application is based on an encrypted protocol and provides an event that is not accessible.
11 . The non-transitory storage medium of claim 9 wherein the network experience score has a non-negative integer value.
12 . The non-transitory storage medium of claim 9 , wherein
the network experience grade is an outstanding grade, a very good grade, a good grade, a satisfactory grade, or a sufficient grade.