Enable access point availability prediction
View Patent ↗In an example, a set of training fingerprints may be access, in which each of the training fingerprints may specify an access point of a plurality of access points to which a mobile device made a successful connection and a cellular signal strength of a cellular tower near the client device when the successful connection was made. An interim model may be generated from the accessed set of training fingerprints, in which the interim model may contain a subset of the information in the set of training fingerprints to enable a destination device to generate a prediction model to predict an availability of an access point. The generated interim model may be transferred to the destination device.
1. A computing device comprising:
a processor; and
a memory on which is stored machine readable instructions that are to cause the processor to:
access a set of training fingerprints, wherein each of the training fingerprints specifies an access point of a plurality of access points to which a mobile device made a successful connection and a cellular signal strength of a cellular tower near the client device when the successful connection was made;
generate an interim model from the accessed set of training fingerprints, the interim model containing a subset of the information in the set of training fingerprints to enable a destination device to genera prediction model to predict an availability of an access point, wherein the interim model is generated according to a type of prediction modeling the destination device is to generate and implement in predicting an availability of the access point; and
transfer the generated interim model to the destination device.
2. The computing device according to claim 1 , wherein the machine readable instructions are further to cause the processor to:
transform the interim model from a first format to a second format, wherein the first format is a format compatible with the computing device and the second format is a format compatible with the destination device.
3. The computing device according to claim 1 , wherein the machine readable instructions are further to cause the processor to:
generate a prediction model from the accessed set of training fingerprints that is to be used to predict an availability of an access point, wherein the interim model differs from the generated prediction model.
4. The computing device according to claim 1 , wherein, to generate the interim model, the machine readable instructions are further to cause the processor to:
generate the interim model to include information that enables an accuracy at which the destination device is able to predict an availability of an access point to be similar to an accuracy at which the computing device is able to predict an availability of an access point through use of a prediction model generated from the access set of training fingerprints.
5. The computing device of claim 1 , wherein the interim model transferred to the destination device is usable to generate a prediction model without performing a training procedure, wherein the prediction model is to predict an access point availability using the generated prediction model.
6. The computing device of claim 5 , wherein the access point availability is predicted based on a cellular tower identifier and a cellular tower signal strength provided as input to the prediction model.
7. A method for enabling access point availability prediction in a destination device, said method comprising:
accessing, by a processor, a set of training fingerprints, wherein each of the training fingerprints specifies an access point of a plurality of access points to which a mobile device successfully connected and a cellular signal strength of a cellular tower corresponding to the connection;
generating, by the processor, an interim model containing a subset of the information in the accessed set of training fingerprints to enable a destination device to predict, based upon the information contained in the interim model, an availability of an access point, wherein the interim model is generated according to a type of prediction modeling the destination device is to generate and implement in predicting an availability of the access point; and
transferring, by the processor, the generated interim model to the destination device.
8. The method according to claim 7 , further comprising:
transforming the interim model from a first format to a second format, wherein the first format s a format compatible with a source device and the second format is a format compatible with the destination device; and
wherein transferring the generated interim model comprises transferring the transformed interim model to the destination device.