Method for predicting a signal and/or service quality and associated device
A method for predicting at least one parameter representative of a signal quality and/or service quality liable to be delivered to a device when it is connected to one radiofrequency antenna among a plurality of antennas that are configured to establish a connection with said device. The method includes: obtaining at least one parameter of decrease in the signal and/or service quality, predicting at least one parameter representative of a signal and/or service quality by applying at least one prediction model configured to predict at least one parameter representative of a signal quality and/or service quality, on the basis of an estimated parameter of decrease in the signal and/or service quality, and of an indication of a moment and of a position of the device for which the prediction must be carried out, the prediction model having been trained beforehand via supervised learning on a training database.
1. A method for predicting at least one parameter representative of a signal quality and/or service quality liable to be delivered to a device when it is connected to one radiofrequency antenna among a plurality of antennas that are configured to establish a connection with said device, the method being implemented by a computer, the method comprising:
a step of obtaining at least one parameter of decrease in the signal and/or service quality,
a step of predicting at least one parameter representative of a signal and/or service quality by applying at least one prediction model configured to predict at least one parameter representative of a signal quality and/or service quality, on the basis of an estimated parameter of decrease in the signal and/or service quality, and of an indication of a moment and of a position of the device for which the prediction must be carried out, the prediction model having been trained beforehand via supervised learning on a training database, the training database comprising, for a plurality of devices:
at least one parameter representative of a signal quality and/or of a service quality when the device is connected to a radiofrequency antenna,
an indicator of the position of the device,
an indicator of a moment of connection of the device to the antenna,
at least one parameter of decrease in the signal and/or service quality, the method being characterized in that:
the prediction step comprises selecting at least one prediction model from among a plurality of prediction models, each prediction model having been trained beforehand via supervised learning using a training database comprising data relating to the devices that are connected to a respective antenna, and
the indicator of the position of the device is a relative position of the device in relation to a respective antenna, the selected prediction model corresponding to the prediction model trained using a training database comprising the relative position of the device in relation to the respective antenna.
2. The prediction method as claimed in claim 1 , wherein the parameter of decrease in signal and/or service quality is an indicator of a meteorological condition affecting the propagation of a radiofrequency signal through the air or a parameter representative of the number of devices connected to an antenna.
3. The prediction method as claimed in claim 2 , wherein the parameter representative of the number of devices connected to the antenna is a measured or predicted number of devices connected to the antenna.
4. The method for predicting at least one parameter representative of a signal and/or service quality as claimed in claim 1 , wherein the relative position of the device comprises an angle and a distance between the device and the respective antenna.
5. The method as claimed in claim 1 , further comprising the prior implementation of training at least one model for predicting at least one parameter representative of a service quality and/or signal quality liable to be delivered by a radiofrequency antenna, comprising:
a step of establishing a training database comprising:
a sub-step of receiving data collected by a plurality of devices, the collected data comprising, for each device:
the measurement of at least one parameter representative of a signal quality and/or of a service quality when the device is connected to a radiofrequency antenna,
the GNSS position of the device when the device is connected to the antenna,
the date and time of connection to the antenna,
a sub-step of estimating, for each device connected to an antenna at a given date and at a given time of connection at least one parameter of decrease in the signal and/or service quality,
a sub-step of creating at least one training database on the basis of at least some of the collected data and of at least some of the parameters of decrease in the signal and/or service quality associated therewith, and
a step training at least one prediction model via supervised learning of at least one parameter representative of a signal quality and/or of a service quality, from a training database.
6. The method as claimed in claim 5 , wherein:
the collected data further comprise an identifier of the antenna to which a device has been connected at a given date and time of connection,
the step of establishing a training database comprises the creation of a plurality of training databases, each training database comprising data relating to the devices connected to a respective antenna having a respective identifier and parameters of decrease in the signal and/or service quality associated therewith,
the training step comprises training a prediction model via supervised learning of at least one parameter representative of a signal quality and/or of a service quality on each training database of the plurality of training databases.
7. The method as claimed in claim 6 , wherein each training database comprises a relative position of each device in relation to the respective antenna at the date and time of connection to the respective antenna.
8. The method as claimed in claim 7 , wherein the relative position of the device in relation to the respective antenna comprises a distance and an angle between the device and the respective antenna.
9. A method for predicting a signal and/or service quality that can be obtained on a predetermined route of a vehicle on a road network by one radiofrequency antenna among a plurality of antennas that are configured to establish a connection with said device, the method being implemented by a computer, the method comprising:
estimating a time and date at which the vehicle should reach a predetermined position on the route
predicting at least one parameter representative of a signal and/or service quality by implementing a prediction method at the determined time and date, at the predetermined position on the route, method comprising:
a step of obtaining at least one parameter of decrease in the signal and/or service quality,
a step of predicting at least one parameter representative of a signal and/or service quality by applying at least one prediction model configured to predict at least one parameter representative of a signal quality and/or service quality, on the basis of an estimated parameter of decrease in the signal and/or service quality, and of an indication of a moment and of a position of the device for which the prediction must be carried out, the prediction model having been trained beforehand via supervised learning on a training database, the training database comprising, for a plurality of devices:
at least one parameter representative of a signal quality and/or of a service quality when the device is connected to a radiofrequency antenna,
an indicator of the position of the device,
an indicator of a moment of connection of the device to the antenna,
at least one parameter of decrease in the signal and/or service quality,
the method being characterized in that;
the prediction step comprises selecting at least one prediction model from among a plurality of prediction models, each prediction model having been trained beforehand via supervised learning using a training database comprising data relating to the devices that are connected to a respective antenna, and
the indicator of the position of the device is a relative position of the device in relation to a respective antenna, the selected prediction model corresponding to the prediction model trained using a training database comprising the relative positon of the device in relation to the respective antenna.
10. A computer configured to implement method for predicting at least one parameter representative of a signal quality and/or service quality liable to be delivered to a device when it is connected to one radiofrequency antenna among a plurality of antennas that are configured to establish a connection with said device, the method being implemented by a computer, the method comprising:
a step of obtaining at least one parameter of decrease in the signal and/or service quality,
a step of predicting at least one parameter representative of a signal and/or service quality by applying at least one prediction model configured to predict at least one parameter representative of a signal quality and/or service quality, on the basis of an estimated parameter of decrease in the signal and/or service quality, and of an indication of a moment and of a position of the device for which the prediction must be carried out, the prediction model having been trained beforehand via supervised learning on a training database, the training database comprising, for a plurality of devices;
at least one parameter representative of a signal quality and/or of a service quality when the device is connected to a radiofrequency antenna,
an indicator of the position of the device,
an indicator of a moment of connection of the device to the antenna,
at least one parameter of decrease in the signal and/or service quality, the method being characterized in that;
the prediction step comprises selecting at least one prediction model from among a plurality of prediction models, each prediction model having been trained beforehand via supervised learning using a training database comprising data relating to the devices that are connected to a respective antenna, and
the indicator of the position of the device is a relative position of the device in relation to a respective antenna, the selected prediction model corresponding to the prediction model trained using a training database comprising the relative position of the device in relation to the respective antenna.