| CPC H04W 4/029 (2018.02) [H04W 4/33 (2018.02)] | 20 Claims |
|
1. A machine learning method for estimating a location of a target wireless device in an indoor environment comprising multiple rooms, the method comprising:
receiving a plurality of training received signal indictor data sets for discrete locations within each of the multiple rooms of the indoor environment, each training received signal indicator data set comprising first received signal indicator values and first corresponding wireless transmitter identifiers for wireless signals received by a test wireless device at a respective discrete location, from wireless access points within the indoor environment;
generating feature vectors from the training received signal indicator data sets;
training a machine learning model using the feature vectors to obtain a trained machine learning model;
receiving a target received signal data set from the target wireless device, the target received signal data set comprising second received signal indicator values and second corresponding wireless transmitter identifiers for wireless signals received by the target wireless device from one or more of the wireless access points within the indoor environment;
generating a target feature vector from the target received signal data set; and
estimating a location of the target wireless device, within one of the multiple rooms, as a discrete location output by the trained machine learning model in response to the target feature vector.
|